Resources


Database Credentialed Access

MIMIC-IV-Ext Cardiac Disease

Jiawei Cao, Sendong Zhao

The subset of the MIMIC-IV dataset includes the examination results and diagnostic information of 4,761 cardiac disease patients. The examination results for each patient are listed separately as evidence for the final diagnosis.

Published: May 6, 2025. Version: 1.0.0

Database Credentialed Access

RadGraph: Extracting Clinical Entities and Relations from Radiology Reports

Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Matthew Lungren, Andrew Ng, Curtis Langlotz, Pranav Rajpurkar

RadGraph is a dataset of entities and relations in full-text chest X-ray radiology reports, which are obtained using a novel information extraction (IE) schema to capture clinically relevant information in a radiology report.

entity and relation extraction graph multi-modal natural language processing radiology

Published: June 3, 2021. Version: 1.0.0

Database Credentialed Access

ODD: A Benchmark Dataset for the NLP-based Opioid Related Aberrant Behavior Detection

Sunjae Kwon, Xun Wang, Weisong Liu, Emily Druhl, Minhee Sung, Joel Reisman, Wenjun Li, Robert Kerns, William Becker, Hong Yu

Opioid-related aberrant behaviors (ORABs) detection Dataset (ODD) which is a large-size, expert-annotated, and multi-label classification benchmark dataset corresponding to the task

substance use natural language processing opioid related aberrant behavior

Published: Jan. 11, 2024. Version: 1.0.0

Database Credentialed Access

MedNLI for Shared Task at ACL BioNLP 2019

Chaitanya Shivade

Data for the MedNLI Shared Task at the 2019 ACL BioNLP 2019 Workshop on Biomedical Language Processing

natural language inference recognizing textual entailment mimic

Published: Nov. 28, 2019. Version: 1.0.1

Model Credentialed Access

Clinical-T5: Large Language Models Built Using MIMIC Clinical Text

Eric Lehman, Alistair Johnson

We train a T5-Base and T5-Large from scratch on MIMIC-III and MIMIC-IV. Additionally, we further pretrain T5-Base and SciFive on notes from MIMIC. We release these model weights on PhysioNet.

Published: Jan. 25, 2023. Version: 1.0.0

Model Credentialed Access

EntityBERT: BERT-based Models Pretrained on MIMIC-III with or without Entity-centric Masking Strategy for the Clinical Domain

Chen Lin, Steven Bethard, Guergana Savova, Timothy Miller, Dmitriy Dligach

Pretraining of models with a broad representation of biomedical terminology (PubMedBERT) on MIMIC-III corpus along with or without a novel entity-centric masking strategy.

Published: March 17, 2022. Version: 1.0.1

Challenge Credentialed Access

Analysis of Clinical Text: Task 14 of SemEval 2015

Guergana Savova

This is the dataset for SemEval 2014 and 2015, Analysis of Clinical Text

semeval nlp

Published: Dec. 28, 2014. Version: 2.0

Database Credentialed Access

CXR-PRO: MIMIC-CXR with Prior References Omitted

Vignav Ramesh, Nathan Chi, Pranav Rajpurkar

CXR-PRO is an adaptation of the MIMIC-CXR dataset (consisting of chest radiographs and their associated free-text radiology reports) with references to non-existent priors removed.

generation free-text radiology reports references to priors retrieval large language models

Published: Nov. 23, 2022. Version: 1.0.0

Database Restricted Access

Swiss-Mammo: A physician-written, synthetic dataset of German mammography reports

Daniel Reichenpfader, Sandro von Däniken, Harald Marcel Bonel

Swiss-Mammo: A physician-written, synthetic dataset of 28 German mammography reports. The dataset is stratified based on BI-RADS categories and available in German and English.

radiology mammography structured reporting bi-rads

Published: June 24, 2025. Version: 1.0.1

Database Credentialed Access

Tasks 1 and 3 from Progress Note Understanding Suite of Tasks: SOAP Note Tagging and Problem List Summarization

Yanjun Gao, John Caskey, Timothy Miller, Brihat Sharma, Matthew Churpek, Dmitriy Dligach, Majid Afshar

We introduce a hierarchical annotation suite of tasks addressing clinical text understanding, reasoning and abstraction over evidence, and diagnosis summarization. One task is section tagging major section and the other task is diagnosis generation.

Published: Sept. 30, 2022. Version: 1.0.0