Identifying ARDS using the Hierarchical Attention Network with Sentence Objectives Framework
This work addresses the challenge of late ARDS diagnosis, especially in COVID-19 patients, by enabling more efficient identification for clinicians and researchers, though it is incremental as it builds on existing hierarchical attention networks.
The paper tackled the problem of automatically identifying ARDS indicators in chest radiograph reports, achieving an F1 score of 0.87 for detecting bilateral infiltrates, comparable to human annotations at 0.84.
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.