Resources


Database Credentialed Access

Learning to Ask Like a Physician: a Discharge Summary Clinical Questions (DiSCQ) Dataset

Eric Lehman

Dataset of questions asked by medical experts about patients. Medical experts will read a discharge summary line-by-line and (1) ask any question that they may have and (2) record what in the text "triggered" them to ask their question.

question generation question answering machine learning

Published: July 28, 2022. Version: 1.0

Software Open Access

AFVP - A Realistic Ventricular Rhythm Model During AF

AFVP generates a synthesized beat-to-beat interval sequence of ventricular excitations with a realistic structure observed during AF.

interbeat rr interval simulation

Published: Aug. 9, 2007. 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

MIMIC-III-Ext-VeriFact-BHC: Labeled Propositions From Brief Hospital Course Summaries for Long-form Clinical Text Evaluation

Philip Chung, Akshay Swaminathan, Alex Goodell, Yeasul Kim, Momsen Reincke, Lichy Han, Ben Deverett, Mohammad Amin Sadeghi, Abdel badih El Ariss, Marc Ghanem, David Seong, Andrew Lee, Caitlin Coombes, Brad Bradshaw, Mahir Sufian, Hyo Jung Hong, Teresa Nguyen, Mohammad Rasouli, Komal Kamra, Mark Burbridge, James McAvoy, Roya Saffary, Stephen Parnell Ma, Dev Dash, James Xie, Ellen Wang, Cliff Schmiesing, Nigam Shah, Nima Aghaeepour

A clinician-labeled dataset for fact-checking long-form clinical text against patient EHRs. The dataset contains LLM-written and human-written Brief Hospital Course summaries decomposed to atomic claim and sentence propositions with annotations.

artificial intelligence natural language processing clinical notes electronic health records large language models brief hospital course long-form text chart review text reranking atomic claim hybrid retrieval clinical informatics clinical medicine fact verification retrieval-augmented generation logical atomism text embedding formal logic llm-as-a-judge llm evaluation

Published: April 9, 2025. Version: 1.0.0

Database Credentialed Access

ReFiSco: Report Fix and Score Dataset for Radiology Report Generation

Katherine Tian, Sina J Hartung, Andrew A Li, Jaehwan Jeong, Fardad Behzadi, Juan Calle-Toro, Subathra Adithan, Michael Pohlen, David Osayande, Pranav Rajpurkar

Preliminary human expert evaluation study on 60 MIMIC-CXR radiology reports

Published: Aug. 23, 2023. Version: 0.0

Database Credentialed Access

MedVAL-Bench: Expert-Annotated Medical Text Validation Benchmark

Asad Aali, Vasiliki Bikia, Maya Varma, Nicole Chiou, Sophie Ostmeier, Arnav Singhvi, Magdalini Paschali, Ashwin Kumar, Andrew Johnston, Karimar Amador Martinez, Eduardo Perez Guerrero, Paola Cruz Rivera, Sergios Gatidis, Christian Bluethgen, Eduardo Pontes Reis, Eddy Zandee van Rilland, Poonam Hosamani, Kevin Keet, Minjoung Go, Evelyn Ling, David Larson, Curtis Langlotz, Roxana Daneshjou, Jason Hom, Sanmi Koyejo, Emily Alsentzer, Akshay Chaudhari

MedVAL-Bench is the first large-scale physician-validated benchmark for medical text validation, spanning 6 diverse medical tasks and containing 840 language model-generated outputs annotated by 12 physicians with error assessments and risk grades.

Published: Nov. 14, 2025. Version: 1.0.1

Database Credentialed Access

Symile-MIMIC: a multimodal clinical dataset of chest X-rays, electrocardiograms, and blood labs from MIMIC-IV

Adriel Saporta, Aahlad Manas Puli, Mark Goldstein, Rajesh Ranganath

A multimodal clinical dataset consisting of CXRs, ECGs, and blood labs, designed to evaluate Symile, a simple contrastive loss that accommodates any number of modalities and allows any model to produce representations for each modality.

database cxr ecg chest x-ray mimic contrastive learning model multimodal electrocardiogram

Published: Jan. 28, 2025. Version: 1.0.0

Database Credentialed Access

Symile-MIMIC: a multimodal clinical dataset of chest X-rays, electrocardiograms, and blood labs from MIMIC-IV

Adriel Saporta, Aahlad Manas Puli, Mark Goldstein, Rajesh Ranganath

A multimodal clinical dataset consisting of CXRs, ECGs, and blood labs, designed to evaluate Symile, a simple contrastive loss that accommodates any number of modalities and allows any model to produce representations for each modality.

database cxr ecg chest x-ray mimic contrastive learning model multimodal electrocardiogram

Published: Jan. 28, 2025. Version: 1.0.0

Database Credentialed Access

Chest X-ray Dataset with Lung Segmentation

Wimukthi Indeewara, Mahela Hennayake, Kasun Rathnayake, Thanuja Ambegoda, Dulani Meedeniya

CXLSeg dataset: Chest X-ray with Lung Segmentation, a comparatively large dataset of segmented Chest X-ray radiographs based on the MIMIC-CXR dataset. This contains segmentation results of 243,324 frontal view images and corresponding masks.

segmentation medical reports u-net chest radiographs mimic-cxr chest x-ray

Published: Feb. 8, 2023. Version: 1.0.0

Database Credentialed Access

MIMIC-Ext-CXR-QBA: A Structured, Tagged, and Localized Visual Question Answering Dataset with Question-Box-Answer Triplets and Scene Graphs for Chest X-ray Images

Philip Müller, Friederike Jungmann, Georgios Kaissis, Daniel Rueckert

We present a large-scale CXR VQA dataset derived from MIMIC-CXR with 42M QA pairs, featuring hierarchical answers, bounding boxes, and structured tags. We generated QA-pairs using LLM-based extraction from radiology reports and localization models.

chest x-rays vqa localization scene graphs

Published: July 22, 2025. Version: 1.0.0