Resources


Database Credentialed Access

TherLid: A Thermometry Linked Dataset

Jeremy Tan, Inês Martins, João Matos, Tiago Filipe Sousa Gonçalves, Tetsu Ohnuma, Jaime dos Santos Cardoso, Leo Anthony Celi, Vijay Krishnamoorthy, Andrea Lane, An Kwok Wong

TherLiD is an open-source dataset of 13,251 paired temperature readings (contact and infrared) from MIMIC-IV and eICU databases. With added demographics and derived data, it supports research on racial and ethnic disparities in infrared thermometry.

thermometry intensive care unit health equity electronic health records

Published: Jan. 21, 2025. Version: 1.0.0


Database Credentialed Access

ENCoDE, mEasuring skiN Color to correct pulse Oximetry DisparitiEs: skin tone and clinical data from a prospective trial on acute care patients.

Sicheng Hao, Katelyn Dempsey, João Matos, Mahmoud Alwakeel, Jared Houghtaling, An Kwok Wong

A prospective collected EHR-linked skin tone measurements database in OMOP format with emphasis on pulse oximetry disparities.

Published: Aug. 22, 2024. Version: 1.0.0


Database Credentialed Access

EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries

Sunjun Kweon, Jiyoun Kim, Heeyoung Kwak, Dongchul Cha, Hangyul Yoon, Kwang Hyun Kim, Jeewon Yang, Seunghyun Won, Edward Choi

An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries

Published: June 26, 2024. Version: 1.0.1


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


Challenge Credentialed Access

BioNLP Workshop 2023 Shared Task 1A: Problem List Summarization

Yanjun Gao, Dmitriy Dligach, Timothy Miller, Majid Afshar

This is the data storage for BioNLP Workshop Shared Task 1A: Problem List Summarization.

bionlp clinical natural language processing electronic health record summarization

Published: Nov. 12, 2023. Version: 2.0.0


Database Credentialed Access

BOLD, a blood-gas and oximetry linked dataset

João Matos, Tristan Struja, Jack Gallifant, Luis Filipe Nakayama, Marie Charpignon, Xiaoli Liu, Jaime dos Santos Cardoso, Leo Anthony Celi, An Kwok Wong

An open-source pulse oximetry and arterial blood gas dataset, derived from MIMIC-III, MIMIC-IV, and eICU-CRD

pulse oximetry intensive care unit health equity electronic health records

Published: Nov. 8, 2023. Version: 1.0


Database Open Access

MIMIC-IV Clinical Database Demo

Alistair Johnson, Lucas Bulgarelli, Tom Pollard, Steven Horng, Leo Anthony Celi, Roger Mark

An openly available subset of patients in the MIMIC-IV database.

critical care electronic health record mimic

Published: Jan. 31, 2023. Version: 2.2


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


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


Model Credentialed Access

Clinical BERT Models Trained on Pseudo Re-identified MIMIC-III Notes

Eric Lehman, Sarthak Jain, Karl Pichotta, Yoav Goldberg, Byron Wallace

We explore recovering sensitive info from BERT trained over non-deidentified EHR. We make our models and data available to further facilitate research.

Published: April 28, 2021. Version: 1.0.0