University of Washington, Seattle, WA, USA.
AMIA Annu Symp Proc. 2022 Feb 21;2021:823-832. eCollection 2021.
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.
急性呼吸窘迫综合征（ARDS）是一种危及生命的疾病，常被漏诊或误诊。ARDS 在感染 COVID-19 的人群中尤为突出。我们探讨了在自由文本胸部 X 光报告中自动识别 ARDS 指标和混杂因素。我们提出了一个新的胸部 X 光报告注释语料库，并介绍了带有句子目标的分层注意网络（HANSO）文本分类框架。HANSO 利用细粒度注释来提高文档分类性能。HANSO 可以通过利用关系注释来提取与 ARDS 相关的信息，即使注释跨度存在噪声。使用注释的胸部 X 光图像作为黄金标准，HANSO 在胸部 X 光报告中识别出双侧浸润，这是 ARDS 的一个指标，其性能（0.87 F1）与人类注释（0.84 F1）相当。该算法可以帮助临床医生和研究人员更有效地识别 ARDS，并有助于开发新的治疗方法，改善患者的护理。
