Datasets

Purpose

This file includes datasets that are relevant to the Patient Discharge Summarization use case.

Datasets List

Name of Dataset

Description

Link

Discharge Me: BioNLP ACL’24 Shared Task on Streamlining Discharge Documentation

“The full dataset (comprised of a defined training, validation, phase 1 testing, and phase 2 testing sets) consists of 109,168 emergency department admissions. The competition is being hosted on the Codabench platform, which will manage team registration, results submission, and score evaluation.”

Discharge Me Dataset

MedDec: Medical Decisions for Discharge Summaries in the MIMIC-III Database

“The MedDec dataset includes expert-annotated decisions of ten types, including defining problems, setting treatment goals, making drug-related decisions, performing therapeutic procedures, giving advice and precautions, and deferment decisions. It spans across eleven diverse patient phenotypes such as heart disease, lung disease, cancer, psychiatric disorders, and chronic pain, from 451 expert-annotated discharge summaries in the MIMIC-III database.”

MedDec Dataset