Identifying ARDS using the Hierarchical Attention Network with Sentence Objectives Framework

TL;DR

This paper introduces HANSO, a hierarchical attention-based framework that automatically identifies ARDS indicators from chest radiograph reports with high accuracy, aiding timely diagnosis and treatment.

Contribution

The study presents a novel annotated corpus and a new text classification framework, HANSO, that effectively extracts ARDS-related information from noisy free-text radiograph reports.

Findings

HANSO achieves 0.87 F1 in identifying bilateral infiltrates.

HANSO's performance is comparable to human annotations.

The framework improves automatic ARDS detection from radiograph reports.

Abstract

Acute respiratory distress syndrome (ARDS) is a life-threatening condition that is often undiagnosed or diagnosed late. ARDS is especially prominent in those infected with COVID-19. We explore the automatic identification of ARDS indicators and confounding factors in free-text chest radiograph reports. We present a new annotated corpus of chest radiograph reports and introduce the Hierarchical Attention Network with Sentence Objectives (HANSO) text classification framework. HANSO utilizes fine-grained annotations to improve document classification performance. HANSO can extract ARDS-related information with high performance by leveraging relation annotations, even if the annotated spans are noisy. Using annotated chest radiograph images as a gold standard, HANSO identifies bilateral infiltrates, an indicator of ARDS, in chest radiograph reports with performance (0.87 F1) comparable to human annotations (0.84 F1). This algorithm could facilitate more efficient and expeditious identification of ARDS by clinicians and researchers and contribute to the development of new therapies to improve patient care.