Identifying Condition-Action Statements in Medical Guidelines Using Domain-Independent Features

TL;DR

This paper introduces new datasets and machine learning baselines for extracting condition-action pairs from medical guidelines, moving beyond rule-based methods to improve automated understanding of clinical texts.

Contribution

It provides two annotated datasets and demonstrates supervised machine learning techniques for identifying condition-action statements in medical guidelines, highlighting limitations and future directions.

Findings

Supervised ML techniques outperform rule-based methods.

New annotated datasets facilitate research in medical text mining.

Identified limitations suggest avenues for future improvements.

Abstract

This paper advances the state of the art in text understanding of medical guidelines by releasing two new annotated clinical guidelines datasets, and establishing baselines for using machine learning to extract condition-action pairs. In contrast to prior work that relies on manually created rules, we report experiment with several supervised machine learning techniques to classify sentences as to whether they express conditions and actions. We show the limitations and possible extensions of this work on text mining of medical guidelines.