Cohort characteristics.

BackgroundDyspnoea is one of the emergency department’s (ED) most common and deadly chief complaints, but frequently misdiagnosed and mistreated. We aimed to design a diagnostic decision support which classifies dyspnoeic ED visits into acute heart failure (AHF), exacerbation of chronic obstructive pulmonary disease (eCOPD), pneumonia and “other diagnoses” by using deep learning and complete, unselected data from an entire regional health care system.MethodsIn this cross-sectional study, we included all dyspnoeic ED visits of patients ≥ 18 years of age at the two EDs in the region of Halland, Sweden, 07/01/2017–12/31/2019. Data from the complete regional health care system within five years prior to the ED visit were analysed. Gold standard diagnoses were defined as the subsequent in-hospital or ED discharge notes, and a subsample was manually reviewed by emergency medicine experts. A novel deep learning model, the clinical attention-based recurrent encoder network (CareNet), was developed. Cohort performance was compared to a simpler CatBoost model. A list of all variables and their importance for diagnosis was created. For each unique patient visit, the model selected the most important variables, analysed them and presented them to the clinician interpretably by taking event time and clinical context into account. AUROC, sensitivity and specificity were compared.FindingsThe most prevalent diagnoses among the 10,315 dyspnoeic ED visits were AHF (15.5%), eCOPD (14.0%) and pneumonia (13.3%). Median number of unique events, i.e., registered clinical data with time stamps, per ED visit was 1,095 (IQR 459–2,310). CareNet median AUROC was 87.0%, substantially higher than the CatBoost model´s (81.4%). CareNet median sensitivity for AHF, eCOPD, and pneumonia was 74.5%, 92.6%, and 54.1%, respectively, with a specificity set above 75.0, slightly inferior to that of the CatBoost baseline model. The model assembled a list of 1,596 variables by importance for diagnosis, on top were prior diagnoses of heart failure or COPD, daily smoking, atrial fibrillation/flutter, life management difficulties and maternity care. Each patient visit received their own unique attention plot, graphically displaying important clinical events for the diagnosis.InterpretationWe designed a novel interpretable deep learning model for diagnosis in emergency department dyspnoea patients by analysing unselected data from a complete regional health care system.背景：呼吸困难（dyspnoea）是急诊科（emergency department, ED）最常见且致命的主诉之一，但常被误诊与误治。本研究旨在开发一款诊断决策支持工具，通过深度学习方法，利用某区域医疗系统完整且未经筛选的全部数据，将因呼吸困难就诊的急诊科患者划分为急性心力衰竭（acute heart failure, AHF）、慢性阻塞性肺疾病急性加重（exacerbation of chronic obstructive pulmonary disease, eCOPD）、肺炎及“其他诊断”四类。 方法：本项横断面研究纳入了2017年7月1日至2019年12月31日期间，瑞典哈兰地区两家急诊科收治的所有18岁及以上因呼吸困难就诊的患者病例。研究分析了患者在急诊科就诊前五年内来自该区域完整医疗系统的全部数据。金标准诊断定义为后续的住院或急诊科出院记录，且由急诊医学专家对亚样本进行了人工复核。本研究开发了一款新型深度学习模型——基于临床注意力机制的循环编码器网络（clinical attention-based recurrent encoder network, CareNet），并将其队列性能与更为简洁的CatBoost模型进行对比。研究构建了全部变量及其诊断重要性的列表，针对每一次唯一的患者就诊记录，模型会选取关键变量进行分析，并结合事件发生时间与临床背景，以可解释的方式将结果呈现给临床医师。同时比较了两种模型的受试者工作特征曲线下面积（AUROC）、灵敏度与特异度。 结果：在10315次因呼吸困难就诊的急诊科病例中，最常见的诊断为急性心力衰竭（15.5%）、慢性阻塞性肺疾病急性加重（14.0%）与肺炎（13.3%）。每次急诊科就诊对应的唯一事件（即带时间戳的已登记临床数据）的中位数为1095（四分位距IQR 459~2310）。CareNet的受试者工作特征曲线下面积中位数为87.0%，显著高于CatBoost模型的81.4%。针对急性心力衰竭、慢性阻塞性肺疾病急性加重与肺炎，CareNet的中位灵敏度分别为74.5%、92.6%与54.1%，其特异度设定高于75.0%，略逊于CatBoost基准模型。本模型共生成了1596个按诊断重要性排序的变量列表，排名靠前的变量包括心力衰竭或慢性阻塞性肺疾病既往病史、每日吸烟史、心房颤动/心房扑动、生活管理困难与产科护理。每一次患者就诊均可生成专属的注意力图谱，以图形化方式展示对诊断具有重要意义的临床事件。 解读：本研究通过分析某区域完整医疗系统的未经筛选数据，开发了一款新型可解释的深度学习模型，用于急诊科呼吸困难患者的诊断。