Resources


Database Credentialed Access

Annotation dataset of problematic opioid use and related contexts from MIMIC-III Critical Care Database discharge summaries

Melissa Poulsen, Vanessa Troiani, Philip Freda, Danielle Mowery, Anahita Davoudi

The database contains a corpus of annotated data from the MIMIC-III Critical Care Database from a study that aimed to develop and apply an annotation schema to characterize opioid use disorder and related contextual factors.

natural language processing opioid use disorder clinical notes substance use

Published: Feb. 8, 2023. Version: 1.0.0

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

Database Credentialed Access

Nosocomial Risk Datasets from MIMIC-III

Travis Goodwin

Text-based Longitudinal Data for Predicting Nosocomial Disease Risk as used by CANTRIP.

deep learning natural language processing pressure injury risk prediction acute kidney injury anemia forecasting

Published: Sept. 15, 2022. Version: 1.0

Database Credentialed Access

Chest X-ray segmentation images based on MIMIC-CXR

Li-Ching Chen, Po-Chih Kuo, Ryan Wang, Judy Gichoya, Leo Anthony Celi

A chest x-rays segmentation dataset derived from MIMIC-CXR based on deep learning algorithm and human examination.

segmentation chest x-rays cxr

Published: Aug. 18, 2022. Version: 1.0.0

Database Credentialed Access

Synthetic Acute Hypotension and Sepsis Datasets Based on MIMIC-III and Published as Part of the Health Gym Project

Nicholas Kuo, Simon Finfer, Louisa Jorm, Sebastiano Barbieri

This repository hosts the original Health Gym datasets of Acute Hypotension and Sepsis

sepsis machine learning acute hypotension reinforcement learning synthetic dataset generative modelling wasserstein generative adversarial network

Published: Feb. 23, 2022. Version: 1.0.0

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

Database Credentialed Access

National Institutes of Health Stroke Scale (NIHSS) Annotations for the MIMIC-III Database

Jiayang Wang, Xiaoshuo Huang, Lin Yang, Jiao Li

A dataset of annotated NIHSS scale items and corresponding scores from stroke patients discharge summaries in MIMIC-III.

Published: Jan. 25, 2021. Version: 1.0.0

Database Credentialed Access

Annotated Question-Answer Pairs for Clinical Notes in the MIMIC-III Database

Xiang Yue, Xinliang Frederick Zhang, Huan Sun

Annotated Question Answering Pairs for Clinical Notes in the MIMIC-III Database

clinical question answering clinical nlp clinical reading comprehension

Published: Jan. 15, 2021. Version: 1.0.0

Model Credentialed Access

Transformer models trained on MIMIC-III to generate synthetic patient notes

Ali Amin-Nejad, Julia Ive, Sumithra Velupillai

Machine learning models that have been trained using MIMIC-III to enable the creation of synthetic discharge summaries.

Published: May 27, 2020. Version: 1.0.0

Database Credentialed Access

Phenotype Annotations for Patient Notes in the MIMIC-III Database

Edward Moseley, Leo Anthony Celi, Joy Wu, Franck Dernoncourt

Clinical notes, annotated by at least two expert annotators for over ten patient phenotypes, including advanced cancer, substance abuse, and treatment non-adherence.

patient classification natural language processing

Published: March 5, 2020. Version: 1.20.03