Ontology-driven weak supervision for clinical entity classification in electronic health records

TL;DR

This paper introduces Trove, a weak supervision framework leveraging medical ontologies and expert rules to classify clinical entities in electronic health records, enabling efficient, privacy-preserving model training with performance comparable to manual labeling.

Contribution

The paper presents Trove, a novel weak supervision approach that uses ontologies and rules for clinical entity classification, reducing reliance on manual annotations and facilitating data sharing.

Findings

Trove achieves comparable performance to manual labeling on six benchmark tasks.

Trove effectively analyzes COVID-19 patient records from emergency visits.

The framework enables rapid, privacy-preserving model development for clinical notes.

Abstract

In the electronic health record, using clinical notes to identify entities such as disorders and their temporality (e.g. the order of an event relative to a time index) can inform many important analyses. However, creating training data for clinical entity tasks is time consuming and sharing labeled data is challenging due to privacy concerns. The information needs of the COVID-19 pandemic highlight the need for agile methods of training machine learning models for clinical notes. We present Trove, a framework for weakly supervised entity classification using medical ontologies and expert-generated rules. Our approach, unlike hand-labeled notes, is easy to share and modify, while offering performance comparable to learning from manually labeled training data. In this work, we validate our framework on six benchmark tasks and demonstrate Trove's ability to analyze the records of patients visiting the emergency department at Stanford Health Care for COVID-19 presenting symptoms and risk factors.