MedDec: A Dataset for Extracting Medical Decisions from Discharge Summaries

TL;DR

This paper introduces MedDec, a new dataset for extracting and classifying medical decisions from clinical notes, providing a foundation for advancing automated understanding of medical decision-making processes.

Contribution

The paper presents MedDec, a novel annotated dataset for medical decision extraction, along with baseline models and analysis of data complexity in clinical notes.

Findings

MedDec dataset contains annotations for 11 phenotypes and 10 decision types.

Baseline span detection models achieve moderate performance on the dataset.

Analysis reveals significant complexity in extracting medical decisions from clinical notes.

Abstract

Medical decisions directly impact individuals' health and well-being. Extracting decision spans from clinical notes plays a crucial role in understanding medical decision-making processes. In this paper, we develop a new dataset called "MedDec", which contains clinical notes of eleven different phenotypes (diseases) annotated by ten types of medical decisions. We introduce the task of medical decision extraction, aiming to jointly extract and classify different types of medical decisions within clinical notes. We provide a comprehensive analysis of the dataset, develop a span detection model as a baseline for this task, evaluate recent span detection approaches, and employ a few metrics to measure the complexity of data samples. Our findings shed light on the complexities inherent in clinical decision extraction and enable future work in this area of research. The dataset and code are available through https://github.com/CLU-UML/MedDec.