| DEDUCE |
|
Deidentification |
Yes |
Yes |
Mosteiro |
2025 |
Investigating De-Identification Methodologies in Dutch Medical Texts: A Replication Study of Deduce and Deidentify |
link |
| DEDUCE |
Removal of Protected Health Information |
Deidentification |
Yes |
Yes |
Menger |
2018 |
DEDUCE: A pattern matching method for automatic de- identification of Dutch medical text |
link |
| Scheurwegs-OMSVM |
|
Deidentification |
No |
Yes |
Scheurwegs |
2013 |
De-Identification of Clinical Free Text in Dutch with Limited Training Data: A Case Study |
|
| Scheurwegs-OOSVM |
|
Deidentification |
No |
Yes |
Scheurwegs |
2013 |
De-Identification of Clinical Free Text in Dutch with Limited Training Data: A Case Study |
|
| Scheurwegs-RF10 |
|
Deidentification |
No |
Yes |
Scheurwegs |
2013 |
De-Identification of Clinical Free Text in Dutch with Limited Training Data: A Case Study |
|
| T25-DeepSeek-R1-14B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Domain-BERT-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Domain-Longformer-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Domain-Longformer-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Domain-RoBERTa-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Domain-RoBERTa-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Gemma-2-2B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Gemma-2-9B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-General-BERT-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-General-Longformer-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-General-Longformer-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-General-RoBERTa-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-General-RoBERTa-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Llama-3.1-8B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Llama-3.2-3B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Llama-3.3-70B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Mistral-Nemo-12B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Mixed-BERT-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Mixed-Longformer-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Mixed-Longformer-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Mixed-RoBERTa-base |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Mixed-RoBERTa-large |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T25-Phi-4-14B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T25-Qwen-2.5-14B |
Task 25: Anonymization, sequence tagging |
Deidentification |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| Trienes-BiLSTM-CRF |
|
Deidentification |
Yes |
Yes |
Mosteiro |
2025 |
Investigating De-Identification Methodologies in Dutch Medical Texts: A Replication Study of Deduce and Deidentify |
|
| Trienes-BiLSTM-CRF |
|
Deidentification |
Yes |
Yes |
Trienes |
2020 |
Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records |
|
| Trienes-CRF |
|
Deidentification |
Yes |
Yes |
Trienes |
2020 |
Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records |
|
| Trienes-DEDUCE |
|
Deidentification |
Yes |
Yes |
Trienes |
2020 |
Comparing Rule-based, Feature-based and Deep Neural Methods for De-identification of Dutch Medical Records |
|
| Autoscriber |
Clinical conversation summarization (digital scribe) |
Generative applications |
No |
Yes |
van Buchem |
2024 |
Impact of a Digital Scribe System on Clinical Documentation Time and Quality: Usability Study |
link |
| GPT-4 |
Medical text summarization |
Generative applications |
No |
No |
Schoonbeek |
2025 |
Completeness, correctness and conciseness of physician-written versus large language model generated patient summaries integrated in electronic health records |
|
| GPT-4 |
Automatic generation of draft replies to patient messages |
Generative applications |
No |
Yes |
Bootsma-Robroeks |
2025 |
AI-generated draft replies to patient messages: exploring effects of implementation |
|
| GPT-4-Turbo version 1106 |
To generate discharge letters from EHR data |
Generative applications |
No |
No |
de Hond |
2025 |
Hallucinations, Omissions, and Usability: A Comparison between GPT-Generated and Physician Discharge Letters for Clinical Use |
link |
| Hybrid (EDA + BI-RADS) |
To automatically summarize Dutch radiology reports and assign a BI-RADS score |
Generative applications |
No |
Yes |
Nguyen |
2020 |
A Hybrid Text Classification and Language Generation Model for Automated Summarization of Dutch Breast Cancer Radiology Reports |
link |
| Arends-ALLRule |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
No |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-BOW |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-CNN |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-MedCAT |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-MedRoBERTa |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
No |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-SetFit-RobBERT |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-SpanCategorizer |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Arends-biGRU |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Arends |
2024 |
Diagnosis extraction from unstructured Dutch echocardiogram reports using span- and document-level characteristic classification |
link |
| Bagheri-AVG-W2V |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-BOW-SVM |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-BiGRU |
ICD-10, specifically the four-character ICD-10 codes that are clinically\nrelevant such as atrial fibrillation (I48), acute myocardial infarction (I21) or dilated cardiomyopathy (I42.0). |
Information extraction |
No |
Yes |
Bagheri |
2021 |
Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks |
link |
| Bagheri-BiLSTM |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-CNN1 |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-CNN2 |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-HA-GRU |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Bagheri-LSTM |
ICD-10 |
Information extraction |
No |
Yes |
Bagheri |
2020 |
Automatic ICD-10 Classification of Diseases from Dutch Discharge Letters |
link |
| Burgt-TM |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
Yes |
Yes |
Burgt |
2024 |
Development of a text mining algorithm for identifying adverse drug reactions in electronic health records |
|
| CDC-CTCue-queries |
We selected two confirmed safety signals and two suspected drug-event associations (hereafter referred to as potential safety signals) generated by the SRS of the Nether- lands Pharmacovigilance Centre Lareb. Targeted searches were performed in the structured and unstructured fields of the EHR to identify additional cases for these signals using a text-mining software CTcue. |
Information extraction |
partially |
Yes |
Kalkhoran |
2024 |
An innovative method to strengthen evidence for potential drug safety signals using Electronic Health Records |
|
| CDC-CTCue-queries |
generally presented in RCTs evaluating new drug therapies in mRCC were collected: Extraction of patient-related characteristics, treatment-related variables, comorbidities, adverse drug events, IMDC-criteria |
Information extraction |
partially |
Yes |
Laar |
2020 |
An Electronic Health Record Text Mining Tool to Collect Real-World Drug Treatment Outcomes: A Validation Study in Patients With Metastatic Renal Cell Carcinoma |
|
| Cara-Llama-3-classify |
WHO performance status classification |
Information extraction |
Yes |
Yes |
Cara |
2025 |
Automating Performance Status Annotation in Oncology Using Llama-3 |
link |
| Cara-Llama-3-score |
WHO performance score regression |
Information extraction |
Yes |
Yes |
Cara |
2025 |
Automating Performance Status Annotation in Oncology Using Llama-3 |
link |
| ContextD |
In this paper we focus on the binary context-property negation. The label negated was given when evidence in the text was found that indicated that a specific event or condition did not take place or exist, otherwise the label not negated was assigned. |
Information extraction |
- |
Yes |
Es |
2023 |
Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods |
link |
| ContextD |
each of the recognized terms in the corpus was annotated for the three contextual properties: negation, temporality, and experiencer. |
Information extraction |
partially |
Yes |
Afzal |
2014 |
ContextD: an algorithm to identify contextual properties of medical terms in a Dutch clinical corpus |
|
| Es-BiLSTM |
In this paper we focus on the binary context-property negation. The label negated was given when evidence in the text was found that indicated that a specific event or condition did not take place or exist, otherwise the label not negated was assigned. |
Information extraction |
No |
Yes |
Es |
2023 |
Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods |
link |
| Es-RoBERTa |
In this paper we focus on the binary context-property negation. The label negated was given when evidence in the text was found that indicated that a specific event or condition did not take place or exist, otherwise the label not negated was assigned. |
Information extraction |
Yes |
No |
Es |
2023 |
Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods |
link |
| Es-Voting ensemble |
In this paper we focus on the binary context-property negation. The label negated was given when evidence in the text was found that indicated that a specific event or condition did not take place or exist, otherwise the label not negated was assigned. |
Information extraction |
No |
Yes |
Es |
2023 |
Negation detection in Dutch clinical texts: an evaluation of rule-based and machine learning methods |
link |
| GPT-3.5 |
To assign BI-RADS categories using only the findings described by the radiologists |
Information extraction |
No |
Yes |
Cozzi |
2024 |
BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study |
link |
| GPT-4 |
To assign BI-RADS categories using only the findings described by the radiologists |
Information extraction |
No |
Yes |
Cozzi |
2024 |
BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study |
link |
| Gemini |
To assign BI-RADS categories using only the findings described by the radiologists |
Information extraction |
No |
Yes |
Cozzi |
2024 |
BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study |
link |
| HAGALBERT |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Hendrix-regex |
to identify pulmonary nodules described in radiol - ogy reports |
Information extraction |
Yes |
No |
Hendrix |
2023 |
Trends in the incidence of pulmonary nodules in chest computed tomography: 10‑year results from two Dutch hospitals |
|
| Homburg-BERT |
Detecting covid-19 consultations |
Information extraction |
No |
Yes |
Homburg |
2023 |
A Natural Language Processing Model for COVID-19 Detection Based on Dutch General Practice Electronic Health Records by Using Bidirectional Encoder Representations From Transformers: Development and Validation Study |
|
| Homburg-BERT |
|
Information extraction |
No |
No |
Veldman |
2025 |
Hasselt Corona Impact Study: Impact of COVID-19 on healthcare seeking in a small Dutch town |
|
| Kim-MedRoberta-FT |
we present an automated coding of natural language descriptions of functioning in EHRs into standardized categories according to ICF (Classification of Functioning, Disability and Health), specifically 9 codes relevant for COVID-19 (Tab 1) |
Information extraction |
Yes |
No |
Kim |
2022 |
Modeling Dutch Medical Texts for Detecting Functional Categories and Levels of COVID-19 Patients |
link |
| Klappe-RB |
Contextual property detection: Uncertainty, Laterality, Temporality extraction |
Information extraction |
Yes |
No |
Klappe |
2021 |
Contextual property detection in Dutch diagnosis descriptions for uncertainty, laterality and temporality |
link |
| Krastman-HW |
To identify patients with diagnoses of a hand or wrist disorder |
Information extraction |
Yes |
Yes |
Krastman |
2024 |
Incidence of hand and wrist disorders in primary care: a retrospective cohort study. |
|
| MedRoBERTa.nl-HAGA |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Muizelaar-NB |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
No |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
|
| Muizelaar-RF |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
No |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
|
| Muizelaar-SGD |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Muizelaar-StrMatch |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
Yes |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Nobel-RB |
quantify T-stage of pulmonary tumors according to the tumor node metastasis (TNM) classification |
Information extraction |
Yes |
No |
Nobel |
2021 |
T-staging pulmonary oncology from radiological reports using natural language processing: translating into a multi-language setting |
link |
| Olthof-ANN-300bi200tri |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-ANN-500bi |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-ANN-500uni |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-BERT |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-NB-300bi200tri |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-NB-500bi |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-NB-500uni |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RB-raw |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
Yes |
No |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RF-300bi200tri |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RF-500bi |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RF-500uni |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RF-all |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-RF-all-fsel |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Olthof-W2V |
classify radiology reports in orthopaedic trauma for the presence of injuries. ; Labeling (presence or absence of pneumothorax and lat- erality based on the information in the radiology report) was per- formed |
Information extraction |
No |
Yes |
Olthof |
2021 |
Machine learning based natural language processing of radiology reports in orthopaedic trauma |
|
| Rietberg-BERTje-End2End |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-BERTje-LR |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-BERTje-RF |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-BERTje-SVM |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-Doc2vec-LR |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-Doc2vec-RF |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-Doc2vec-SVM |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-MedRoBERTa.nl-End2End |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-MedRoBERTa.nl-LR |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-MedRoBERTa.nl-RF |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-MedRoBERTa.nl-SVM |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-RobBERT-End2End |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-RobBERT-LR |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-RobBERT-RF |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-RobBERT-SVM |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-TFIDF-LR |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-TFIDF-RF |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| Rietberg-TFIDF-SVM |
Extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring |
Information extraction |
No |
Yes |
Rietberg |
2023 |
Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models |
link |
| RobBERT-HAGA |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Scheurwegs-ADV |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-AvW2V-LMI |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-BOC |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-BPM |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-CW2V-LMI |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-Dict |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-LMI |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-MajVote |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-NB-BN-BoW |
|
Information extraction |
No |
Yes |
Scheurwegs |
2015 |
Data integration of structured and unstructured sources for assigning clinical codes to patient stays |
|
| Scheurwegs-NB-BN-Early-integration |
|
Information extraction |
No |
Yes |
Scheurwegs |
2015 |
Data integration of structured and unstructured sources for assigning clinical codes to patient stays |
|
| Scheurwegs-NB-BN-Late-integration |
|
Information extraction |
No |
Yes |
Scheurwegs |
2015 |
Data integration of structured and unstructured sources for assigning clinical codes to patient stays |
|
| Scheurwegs-NW2V-LMI |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-NW2V-UMLS-LMI |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Scheurwegs-UMLSN |
ICD-9-CM coding |
Information extraction |
No |
Yes |
Scheurwegs |
2017 |
Assigning clinical codes with data-driven concept representation on Dutch clinical free text |
|
| Schuemie-C4.5 |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-KNN |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-MyC |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-NB |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-RF |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-RIPPER |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Schuemie-SVM |
Classifying GP records as either a liver disorder case or not |
Information extraction |
No |
Yes |
Schuemie |
2012 |
Automating classification of free-text electronic health records for epidemiological studies |
|
| Seinen-AVGEMB-LR |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-AVGEMB-LR |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-AVGEMB-NN |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-AVGEMB-NN |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-AVGEMB-XGB |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-AVGEMB-XGB |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-LR |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-LR |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-NN |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-NN |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-XGB |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-TFIDF-XGB |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Seinen-search-terms |
Classifying free text consults with ICPC codes |
Information extraction |
No |
Yes |
Seinen |
2024 |
Using clinical text to refine unspecific condition codes in Dutch general practitioner EHR data |
|
| Siegersma-RB-W2B-V1 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Siegersma-RB-W2B-V2 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Siegersma-RB-W2B-V3 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Siegersma-RB-W2B-V4 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Siegersma-RB-W2B-V5 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Siegersma-RB-W2B-V6 |
extraction of medication and Adverse Drug Reaction Identification in Clinical Notes |
Information extraction |
No |
Yes |
Siegersma |
2022 |
Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching |
|
| Spyns-RB |
Using many many many idfferent subsystems, parsers etc |
Information extraction |
No |
Yes |
Spyns |
1996 |
A Dutch medical language processor |
|
| Straalen-DD |
A text-mining algorithm to determine the diagnosis "Dupuytren’s contracture" from the free text fields |
Information extraction |
partially |
Yes |
Straalen |
2024 |
The incidence and prevalence of Dupuytren’s disease in primary care: results from a text mining approach on registration data |
|
| T1-DeepSeek-R1-14B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Domain-BERT-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Domain-Longformer-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Domain-Longformer-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Domain-RoBERTa-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Domain-RoBERTa-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Gemma-2-2B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Gemma-2-9B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-General-BERT-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-General-Longformer-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-General-Longformer-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-General-RoBERTa-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-General-RoBERTa-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Llama-3.1-8B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Llama-3.2-3B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Llama-3.3-70B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Mistral-Nemo-12B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Mixed-BERT-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Mixed-Longformer-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Mixed-Longformer-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Mixed-RoBERTa-base |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Mixed-RoBERTa-large |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T1-Phi-4-14B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T1-Qwen-2.5-14B |
Task 1: Adhesion presence. Predict adhesion presence (binary) based on the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-DeepSeek-R1-14B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Domain-BERT-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Domain-Longformer-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Domain-Longformer-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Domain-RoBERTa-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Domain-RoBERTa-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Gemma-2-2B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Gemma-2-9B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-General-BERT-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-General-Longformer-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-General-Longformer-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-General-RoBERTa-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-General-RoBERTa-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Llama-3.1-8B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Llama-3.2-3B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Llama-3.3-70B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Mistral-Nemo-12B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Mixed-BERT-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Mixed-Longformer-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Mixed-Longformer-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Mixed-RoBERTa-base |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Mixed-RoBERTa-large |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T10-Phi-4-14B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T10-Qwen-2.5-14B |
Task 10: Prostate radiology suspicious lesions on prostate MRI, predict the number of PI-RADS 3 – 5 lesions based on the radiology report.\npredic2on as a string, being “0”, “1”, “2”, “3”, or “4”. |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-DeepSeek-R1-14B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Domain-BERT-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Domain-Longformer-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Domain-Longformer-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Domain-RoBERTa-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Domain-RoBERTa-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Gemma-2-2B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Gemma-2-9B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-General-BERT-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-General-Longformer-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-General-Longformer-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-General-RoBERTa-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-General-RoBERTa-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Llama-3.1-8B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Llama-3.2-3B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Llama-3.3-70B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Mistral-Nemo-12B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Mixed-BERT-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Mixed-Longformer-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Mixed-Longformer-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Mixed-RoBERTa-base |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Mixed-RoBERTa-large |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T11-Phi-4-14B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T11-Qwen-2.5-14B |
Task 11: Prostate histopathology significant cancers |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-DeepSeek-R1-14B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Domain-BERT-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Domain-Longformer-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Domain-Longformer-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Domain-RoBERTa-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Domain-RoBERTa-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Gemma-2-2B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Gemma-2-9B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-General-BERT-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-General-Longformer-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-General-Longformer-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-General-RoBERTa-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-General-RoBERTa-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Llama-3.1-8B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Llama-3.2-3B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Llama-3.3-70B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Mistral-Nemo-12B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Mixed-BERT-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Mixed-Longformer-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Mixed-Longformer-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Mixed-RoBERTa-base |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Mixed-RoBERTa-large |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T12-Phi-4-14B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T12-Qwen-2.5-14B |
Task 12: Histopathology tissue type |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-DeepSeek-R1-14B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Domain-BERT-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Domain-Longformer-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Domain-Longformer-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Domain-RoBERTa-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Domain-RoBERTa-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Gemma-2-2B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Gemma-2-9B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-General-BERT-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-General-Longformer-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-General-Longformer-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-General-RoBERTa-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-General-RoBERTa-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Llama-3.1-8B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Llama-3.2-3B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Llama-3.3-70B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Mistral-Nemo-12B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Mixed-BERT-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Mixed-Longformer-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Mixed-Longformer-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Mixed-RoBERTa-base |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Mixed-RoBERTa-large |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T13-Phi-4-14B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T13-Qwen-2.5-14B |
Task 13: Histopathology tissue origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-DeepSeek-R1-14B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Domain-BERT-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Domain-Longformer-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Domain-Longformer-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Domain-RoBERTa-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Domain-RoBERTa-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Gemma-2-2B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Gemma-2-9B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-General-BERT-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-General-Longformer-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-General-Longformer-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-General-RoBERTa-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-General-RoBERTa-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Llama-3.1-8B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Llama-3.2-3B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Llama-3.3-70B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Mistral-Nemo-12B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Mixed-BERT-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Mixed-Longformer-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Mixed-Longformer-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Mixed-RoBERTa-base |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Mixed-RoBERTa-large |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T15-Phi-4-14B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T15-Qwen-2.5-14B |
Task 15: Colon histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-DeepSeek-R1-14B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Domain-BERT-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Domain-Longformer-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Domain-Longformer-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Domain-RoBERTa-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Domain-RoBERTa-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Gemma-2-2B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Gemma-2-9B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-General-BERT-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-General-Longformer-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-General-Longformer-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-General-RoBERTa-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-General-RoBERTa-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Llama-3.1-8B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Llama-3.2-3B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Llama-3.3-70B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Mistral-Nemo-12B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Mixed-BERT-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Mixed-Longformer-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Mixed-Longformer-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Mixed-RoBERTa-base |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Mixed-RoBERTa-large |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T16-Phi-4-14B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T16-Qwen-2.5-14B |
Task 16: RECIST lesion size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-DeepSeek-R1-14B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Domain-BERT-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Domain-Longformer-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Domain-Longformer-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Domain-RoBERTa-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Domain-RoBERTa-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Gemma-2-2B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Gemma-2-9B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-General-BERT-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-General-Longformer-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-General-Longformer-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-General-RoBERTa-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-General-RoBERTa-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Llama-3.1-8B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Llama-3.2-3B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Llama-3.3-70B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Mistral-Nemo-12B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Mixed-BERT-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Mixed-Longformer-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Mixed-Longformer-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Mixed-RoBERTa-base |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Mixed-RoBERTa-large |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T17-Phi-4-14B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T17-Qwen-2.5-14B |
Task 17: Pancreatic ductal adenocarcinoma attributes |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-DeepSeek-R1-14B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Domain-BERT-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Domain-Longformer-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Domain-Longformer-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Domain-RoBERTa-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Domain-RoBERTa-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Gemma-2-2B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Gemma-2-9B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-General-BERT-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-General-Longformer-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-General-Longformer-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-General-RoBERTa-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-General-RoBERTa-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Llama-3.1-8B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Llama-3.2-3B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Llama-3.3-70B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Mistral-Nemo-12B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Mixed-BERT-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Mixed-Longformer-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Mixed-Longformer-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Mixed-RoBERTa-base |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Mixed-RoBERTa-large |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T18-Phi-4-14B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T18-Qwen-2.5-14B |
Task 18: Hip Kellgren-Lawrence scoring |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-DeepSeek-R1-14B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Domain-BERT-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Domain-Longformer-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Domain-Longformer-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Domain-RoBERTa-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Domain-RoBERTa-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Gemma-2-2B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Gemma-2-9B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-General-BERT-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-General-Longformer-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-General-Longformer-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-General-RoBERTa-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-General-RoBERTa-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Llama-3.1-8B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Llama-3.2-3B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Llama-3.3-70B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Mistral-Nemo-12B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Mixed-BERT-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Mixed-Longformer-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Mixed-Longformer-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Mixed-RoBERTa-base |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Mixed-RoBERTa-large |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T19-Phi-4-14B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T19-Qwen-2.5-14B |
Task 19: Prostate volume extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-DeepSeek-R1-14B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Domain-BERT-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Domain-Longformer-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Domain-Longformer-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Domain-RoBERTa-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Domain-RoBERTa-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Gemma-2-2B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Gemma-2-9B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-General-BERT-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-General-Longformer-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-General-Longformer-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-General-RoBERTa-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-General-RoBERTa-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Llama-3.1-8B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Llama-3.2-3B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Llama-3.3-70B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Mistral-Nemo-12B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Mixed-BERT-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Mixed-Longformer-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Mixed-Longformer-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Mixed-RoBERTa-base |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Mixed-RoBERTa-large |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T2-Phi-4-14B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T2-Qwen-2.5-14B |
Task 2: Pulmonary nodule presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-DeepSeek-R1-14B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Domain-BERT-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Domain-Longformer-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Domain-Longformer-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Domain-RoBERTa-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Domain-RoBERTa-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Gemma-2-2B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Gemma-2-9B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-General-BERT-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-General-Longformer-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-General-Longformer-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-General-RoBERTa-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-General-RoBERTa-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Llama-3.1-8B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Llama-3.2-3B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Llama-3.3-70B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Mistral-Nemo-12B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Mixed-BERT-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Mixed-Longformer-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Mixed-Longformer-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Mixed-RoBERTa-base |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Mixed-RoBERTa-large |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T20-Phi-4-14B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T20-Qwen-2.5-14B |
Task 20: Prostate specific antigen extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-DeepSeek-R1-14B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Domain-BERT-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Domain-Longformer-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Domain-Longformer-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Domain-RoBERTa-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Domain-RoBERTa-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Gemma-2-2B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Gemma-2-9B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-General-BERT-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-General-Longformer-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-General-Longformer-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-General-RoBERTa-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-General-RoBERTa-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Llama-3.1-8B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Llama-3.2-3B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Llama-3.3-70B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Mistral-Nemo-12B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Mixed-BERT-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Mixed-Longformer-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Mixed-Longformer-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Mixed-RoBERTa-base |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Mixed-RoBERTa-large |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T21-Phi-4-14B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T21-Qwen-2.5-14B |
Task 21: Prostate specific antigen density extraction |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-DeepSeek-R1-14B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Domain-BERT-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Domain-Longformer-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Domain-Longformer-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Domain-RoBERTa-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Domain-RoBERTa-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Gemma-2-2B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Gemma-2-9B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-General-BERT-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-General-Longformer-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-General-Longformer-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-General-RoBERTa-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-General-RoBERTa-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Llama-3.1-8B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Llama-3.2-3B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Llama-3.3-70B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Mistral-Nemo-12B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Mixed-BERT-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Mixed-Longformer-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Mixed-Longformer-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Mixed-RoBERTa-base |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Mixed-RoBERTa-large |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T22-Phi-4-14B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T22-Qwen-2.5-14B |
Task 22: Pancreatic ductal adenocarcinoma size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-DeepSeek-R1-14B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Domain-BERT-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Domain-Longformer-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Domain-Longformer-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Domain-RoBERTa-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Domain-RoBERTa-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Gemma-2-2B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Gemma-2-9B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-General-BERT-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-General-Longformer-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-General-Longformer-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-General-RoBERTa-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-General-RoBERTa-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Llama-3.1-8B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Llama-3.2-3B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Llama-3.3-70B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Mistral-Nemo-12B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Mixed-BERT-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Mixed-Longformer-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Mixed-Longformer-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Mixed-RoBERTa-base |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Mixed-RoBERTa-large |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T23-Phi-4-14B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T23-Qwen-2.5-14B |
Task 23: Pulmonary nodule size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-DeepSeek-R1-14B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Domain-BERT-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Domain-Longformer-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Domain-Longformer-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Domain-RoBERTa-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Domain-RoBERTa-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Gemma-2-2B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Gemma-2-9B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-General-BERT-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-General-Longformer-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-General-Longformer-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-General-RoBERTa-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-General-RoBERTa-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Llama-3.1-8B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Llama-3.2-3B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Llama-3.3-70B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Mistral-Nemo-12B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Mixed-BERT-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Mixed-Longformer-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Mixed-Longformer-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Mixed-RoBERTa-base |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Mixed-RoBERTa-large |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T24-Phi-4-14B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T24-Qwen-2.5-14B |
Task 24: RECIST lesion size measurement |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-DeepSeek-R1-14B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Domain-BERT-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Domain-Longformer-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Domain-Longformer-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Domain-RoBERTa-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Domain-RoBERTa-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Gemma-2-2B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Gemma-2-9B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-General-BERT-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-General-Longformer-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-General-Longformer-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-General-RoBERTa-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-General-RoBERTa-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Llama-3.1-8B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Llama-3.2-3B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Llama-3.3-70B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Mistral-Nemo-12B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Mixed-BERT-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Mixed-Longformer-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Mixed-Longformer-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Mixed-RoBERTa-base |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Mixed-RoBERTa-large |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T26-Phi-4-14B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T26-Qwen-2.5-14B |
Task 26: Medical terminology recognition |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-DeepSeek-R1-14B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Domain-BERT-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Domain-Longformer-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Domain-Longformer-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Domain-RoBERTa-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Domain-RoBERTa-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Gemma-2-2B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Gemma-2-9B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-General-BERT-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-General-Longformer-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-General-Longformer-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-General-RoBERTa-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-General-RoBERTa-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Llama-3.1-8B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Llama-3.2-3B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Llama-3.3-70B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Mistral-Nemo-12B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Mixed-BERT-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Mixed-Longformer-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Mixed-Longformer-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Mixed-RoBERTa-base |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Mixed-RoBERTa-large |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T27-Phi-4-14B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T27-Qwen-2.5-14B |
Task 27: Prostate biopsy sampling |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-DeepSeek-R1-14B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Domain-BERT-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Domain-Longformer-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Domain-Longformer-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Domain-RoBERTa-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Domain-RoBERTa-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Gemma-2-2B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Gemma-2-9B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-General-BERT-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-General-Longformer-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-General-Longformer-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-General-RoBERTa-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-General-RoBERTa-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Llama-3.1-8B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Llama-3.2-3B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Llama-3.3-70B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Mistral-Nemo-12B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Mixed-BERT-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Mixed-Longformer-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Mixed-Longformer-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Mixed-RoBERTa-base |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Mixed-RoBERTa-large |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T28-Phi-4-14B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T28-Qwen-2.5-14B |
Task 28: Skin histopathology diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-DeepSeek-R1-14B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Domain-BERT-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Domain-Longformer-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Domain-Longformer-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Domain-RoBERTa-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Domain-RoBERTa-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Gemma-2-2B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Gemma-2-9B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-General-BERT-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-General-Longformer-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-General-Longformer-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-General-RoBERTa-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-General-RoBERTa-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Llama-3.1-8B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Llama-3.2-3B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Llama-3.3-70B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Mistral-Nemo-12B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Mixed-BERT-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Mixed-Longformer-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Mixed-Longformer-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Mixed-RoBERTa-base |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Mixed-RoBERTa-large |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T3-Phi-4-14B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T3-Qwen-2.5-14B |
Task 3: Kidney abnormality identification, Classify whether any form of kidney abnormality is men2oned in the radiology report |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-DeepSeek-R1-14B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Domain-BERT-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Domain-Longformer-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Domain-Longformer-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Domain-RoBERTa-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Domain-RoBERTa-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Gemma-2-2B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Gemma-2-9B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-General-BERT-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-General-Longformer-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-General-Longformer-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-General-RoBERTa-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-General-RoBERTa-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Llama-3.1-8B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Llama-3.2-3B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Llama-3.3-70B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Mistral-Nemo-12B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Mixed-BERT-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Mixed-Longformer-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Mixed-Longformer-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Mixed-RoBERTa-base |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Mixed-RoBERTa-large |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T4-Phi-4-14B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T4-Qwen-2.5-14B |
Task 4: Skin histopathology case selection |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-DeepSeek-R1-14B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Domain-BERT-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Domain-Longformer-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Domain-Longformer-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Domain-RoBERTa-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Domain-RoBERTa-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Gemma-2-2B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Gemma-2-9B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-General-BERT-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-General-Longformer-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-General-Longformer-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-General-RoBERTa-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-General-RoBERTa-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Llama-3.1-8B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Llama-3.2-3B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Llama-3.3-70B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Mistral-Nemo-12B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Mixed-BERT-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Mixed-Longformer-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Mixed-Longformer-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Mixed-RoBERTa-base |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Mixed-RoBERTa-large |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T5-Phi-4-14B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T5-Qwen-2.5-14B |
Task 5: RECIST timeline, Predict on a report level whether this is a baseline or follow-up scan, Provide your predic2on as\na confidence score between 0 and 1, where 0 corresponds to False (follow-up report) and 1\ncorresponds to True (baseline report). |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-DeepSeek-R1-14B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Domain-BERT-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Domain-Longformer-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Domain-Longformer-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Domain-RoBERTa-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Domain-RoBERTa-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Gemma-2-2B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Gemma-2-9B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-General-BERT-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-General-Longformer-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-General-Longformer-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-General-RoBERTa-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-General-RoBERTa-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Llama-3.1-8B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Llama-3.2-3B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Llama-3.3-70B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Mistral-Nemo-12B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Mixed-BERT-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Mixed-Longformer-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Mixed-Longformer-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Mixed-RoBERTa-base |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Mixed-RoBERTa-large |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T6-Phi-4-14B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T6-Qwen-2.5-14B |
Task 6: Histopathology cancer origin |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-DeepSeek-R1-14B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Domain-BERT-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Domain-Longformer-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Domain-Longformer-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Domain-RoBERTa-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Domain-RoBERTa-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Gemma-2-2B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Gemma-2-9B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-General-BERT-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-General-Longformer-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-General-Longformer-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-General-RoBERTa-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-General-RoBERTa-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Llama-3.1-8B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Llama-3.2-3B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Llama-3.3-70B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Mistral-Nemo-12B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Mixed-BERT-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Mixed-Longformer-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Mixed-Longformer-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Mixed-RoBERTa-base |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Mixed-RoBERTa-large |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T7-Phi-4-14B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T7-Qwen-2.5-14B |
Task 7: Pulmonary nodule size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-DeepSeek-R1-14B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Domain-BERT-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Domain-Longformer-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Domain-Longformer-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Domain-RoBERTa-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Domain-RoBERTa-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Gemma-2-2B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Gemma-2-9B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-General-BERT-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-General-Longformer-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-General-Longformer-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-General-RoBERTa-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-General-RoBERTa-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Llama-3.1-8B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Llama-3.2-3B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Llama-3.3-70B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Mistral-Nemo-12B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Mixed-BERT-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Mixed-Longformer-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Mixed-Longformer-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Mixed-RoBERTa-base |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Mixed-RoBERTa-large |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T8-Phi-4-14B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T8-Qwen-2.5-14B |
Task 8: Pancreatic ductal adenocarcinoma size presence |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-DeepSeek-R1-14B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Domain-BERT-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Domain-Longformer-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Domain-Longformer-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Domain-RoBERTa-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Domain-RoBERTa-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Gemma-2-2B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Gemma-2-9B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-General-BERT-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-General-Longformer-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-General-Longformer-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-General-RoBERTa-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-General-RoBERTa-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Llama-3.1-8B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Llama-3.2-3B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Llama-3.3-70B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Mistral-Nemo-12B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Mixed-BERT-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Mixed-Longformer-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Mixed-Longformer-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Mixed-RoBERTa-base |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Mixed-RoBERTa-large |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| T9-Phi-4-14B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| T9-Qwen-2.5-14B |
Task 9: Pancreatic ductal adenocarcinoma diagnosis |
Information extraction |
No |
Yes |
Builtjes |
2025 |
Leveraging open-source large language models for clinical information extraction in resource-constrained settings |
link |
| Vandenbussche-All-LR |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-All-NB |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-All-SVM |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-LR |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-Meta-LR |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-Meta-NB |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-Meta-SVM |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-NB |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Vandenbussche-Ngrams-SVM |
Classifying self-reported narratives in either migraine or cluster headache |
Information extraction |
No |
Yes |
Vandenbussche |
2022 |
Using natural language processing to automatically classify written self-reported narratives by patients with migraine or cluster headache |
|
| Verschueren-CTCue-rule-based |
capturing disease progression in electronic health\nrecord (EHR) data of patients with metastatic non– small cell lung cancer (mNSCLC) treated with immunochemotherapy. |
Information extraction |
Yes |
No |
Verschueren |
2024 |
Development and Portability of a Text Mining Algorithm for Capturing Disease Progression in Electronic Health Records of Patients With Stage IV Non–Small Cell Lung Cancer |
|
| Wasylewicz-TM |
extraction of the occurrence and severity of eleven commonly described cardiac characteristics |
Information extraction |
No |
Yes |
Wasylewicz |
2021 |
Identifying adverse drug reactions from free-text electronic hospital health record notes |
|
| belabBERT-HAGA |
lifestyle characteristics classification, specifically on smoking, alcohol and drug usage |
Information extraction |
No |
Yes |
Muizelaar |
2024 |
Extracting patient lifestyle characteristics from Dutch clinical text with BERT models |
link |
| Fivez-W2V-Context |
|
Language normalization, representation, and modeling |
No |
Yes |
Fivez |
2017 |
Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings |
link |
| Fivez-W2V-NoisyChannel |
|
Language normalization, representation, and modeling |
No |
Yes |
Fivez |
2017 |
Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings |
link |
| Marin-AWD-LSTM |
|
Language normalization, representation, and modeling |
No |
Yes |
Marin |
2020 |
Effectiveness of neural language models for word prediction of textual mammography reports |
link |
| Marin-FRAGE-LSTM |
|
Language normalization, representation, and modeling |
No |
Yes |
Marin |
2020 |
Effectiveness of neural language models for word prediction of textual mammography reports |
link |
| Marin-LSTM |
|
Language normalization, representation, and modeling |
No |
Yes |
Marin |
2020 |
Effectiveness of neural language models for word prediction of textual mammography reports |
link |
| MedRoBERTa.nl |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Verkijk |
2021 |
MedRoBERTa.nl: A Language Model for Dutch Electronic Health Records |
link |
| joeranbosma/dragon-bert-base-domain-specific |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-bert-base-mixed-domain |
|
Language normalization, representation, and modeling |
Yes |
No |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-longformer-base-domain-specific\t |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-longformer-base-mixed-domain |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-longformer-large-domain-specific |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-longformer-large-mixed-domain |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-roberta-base-domain-specific |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-roberta-base-mixed-domain\t |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-roberta-large-domain-specific\t |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |
| joeranbosma/dragon-roberta-large-mixed-domain |
|
Language normalization, representation, and modeling |
Yes |
Yes |
Bosma |
2025 |
The DRAGON benchmark for clinical NLP |
link |