Heyman Ellen T, Ashfaq Awais, Ekelund Ulf, Ohlsson Mattias, Björk Jonas, Khoshnood Ardavan M, Lingman Markus
Department of Emergency Medicine, Halland Hospital, Region Halland, Sweden.
Emergency Medicine, Department of Clinical Sciences Lund, Lund University, Lund, Sweden.
PLoS One. 2024 Dec 27;19(12):e0311081. doi: 10.1371/journal.pone.0311081. eCollection 2024.
Dyspnoea 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.
In 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.
The 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.
We 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.
呼吸困难是急诊科最常见且致命的主诉之一，但常被误诊和误治。我们旨在设计一种诊断决策支持系统，通过深度学习以及使用来自整个区域医疗系统的完整、未筛选的数据，将急诊科呼吸困难就诊病例分为急性心力衰竭（AHF）、慢性阻塞性肺疾病急性加重（eCOPD）、肺炎和“其他诊断”。
在这项横断面研究中，我们纳入了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所有年龄≥18岁的呼吸困难患者的急诊科就诊病例。分析了急诊就诊前五年内整个区域医疗系统的完整数据。金标准诊断定义为随后的住院或急诊科出院记录，并有一个子样本由急诊医学专家进行人工审核。开发了一种新型深度学习模型，即基于临床注意力的循环编码器网络（CareNet）。将队列表现与一个更简单的CatBoost模型进行比较。创建了所有变量及其对诊断重要性的列表。对于每一次独特的患者就诊，该模型选择最重要的变量，对其进行分析，并通过考虑事件时间和临床背景以可解释的方式呈现给临床医生。比较了曲线下面积（AUROC）、敏感性和特异性。
在10315例呼吸困难的急诊科就诊病例中，最常见的诊断是AHF（15.5%）、eCOPD（14.0%）和肺炎（13.3%）。每次急诊科就诊的独特事件（即带有时间戳的注册临床数据）的中位数为1095（四分位间距459 - 2310）。CareNet的中位数AUROC为87.0%，显著高于CatBoost模型的（81.4%）。CareNet对AHF、eCOPD和肺炎的中位数敏感性分别为74.5%、92.6%和54.1%，特异性设定在75.0以上，略低于CatBoost基线模型。该模型按诊断重要性汇总了1596个变量的列表，排在首位的是先前的心力衰竭或慢性阻塞性肺疾病诊断、每日吸烟情况、心房颤动/扑动、生活管理困难和产科护理。每次患者就诊都有其独特的注意力图，以图形方式显示诊断的重要临床事件。
我们通过分析来自完整区域医疗系统的未筛选数据，设计了一种用于急诊科呼吸困难患者诊断的新型可解释深度学习模型。
