Extracting COVID-19 Diagnoses and Symptoms From Clinical Text: A New Annotated Corpus and Neural Event Extraction Framework

TL;DR

This paper introduces a new annotated clinical text corpus and a neural event extraction framework to identify COVID-19 diagnoses and symptoms from clinical notes, aiding large-scale epidemiological and clinical research.

Contribution

It provides a novel COVID-19 clinical corpus and a span-based event extraction model with high accuracy for identifying COVID-19 related events and assertions.

Findings

High performance in event and assertion extraction (0.83-0.97 F1).

Automatically extracted symptoms improve COVID-19 test result prediction.

The corpus enables better understanding of COVID-19 clinical presentation.

Abstract

Coronavirus disease 2019 (COVID-19) is a global pandemic. Although much has been learned about the novel coronavirus since its emergence, there are many open questions related to tracking its spread, describing symptomology, predicting the severity of infection, and forecasting healthcare utilization. Free-text clinical notes contain critical information for resolving these questions. Data-driven, automatic information extraction models are needed to use this text-encoded information in large-scale studies. This work presents a new clinical corpus, referred to as the COVID-19 Annotated Clinical Text (CACT) Corpus, which comprises 1,472 notes with detailed annotations characterizing COVID-19 diagnoses, testing, and clinical presentation. We introduce a span-based event extraction model that jointly extracts all annotated phenomena, achieving high performance in identifying COVID-19 and symptom events with associated assertion values (0.83-0.97 F1 for events and 0.73-0.79 F1 for assertions). In a secondary use application, we explored the prediction of COVID-19 test results using structured patient data (e.g. vital signs and laboratory results) and automatically extracted symptom information. The automatically extracted symptoms improve prediction performance, beyond structured data alone.