School of Public Health, National Defense Medical Center, Taipei, Taiwan.
Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center Taipei, Taipei, Taiwan.
J Med Syst. 2023 Jul 31;47(1):81. doi: 10.1007/s10916-023-01980-x.
Emergency department (ED) triage scale determines the priority of patient care and foretells the prognosis. However, the information retrieved from the initial assessment is limited, hindering the risk identification accuracy of triage. Therefore, we sought to develop a 'dynamic' triage system as secondary screening, using artificial intelligence (AI) techniques to integrate information from initial assessment data and subsequent examinations. This retrospective cohort study included 134,112 ED visits with at least one electrocardiography (ECG) and chest X-ray (CXR) in a medical center from 2012 to 2022. Additionally, an independent community hospital provided 45,614 ED visits as an external validation set. We trained an eXtreme gradient boosting (XGB) model using initial assessment data to predict all-cause mortality in 7 days. Two deep learning models (DLMs) using ECG and CXR were trained to stratify mortality risks. The dynamic triage levels were based on output from the XGB-triage and DLMs from ECG and CXR. During the internal and external validation, the area under the receiver operating characteristic curve (AUC) of the XGB-triage model was >0.866; furthermore, the AUCs of DLMs using ECG and CXR were >0.862 and >0.886, respectively. The dynamic triage scale provided a higher C-index (0.914-0.920 vs. 0.827-0.843) than the original one and demonstrated better predictive ability for 5-year mortality, 30-day ED revisit, and 30-day discharge. The AI-based risk scale provides a more accurate and dynamic stratification of mortality risk in ED patients, particularly in identifying patients who tend to be overlooked due to atypical symptoms.
急诊科分诊量表决定了患者护理的优先级，并预测预后。然而，初始评估所获取的信息有限，这阻碍了分诊的风险识别准确性。因此，我们试图开发一种“动态”分诊系统作为二级筛查，利用人工智能（AI）技术整合初始评估数据和后续检查的信息。这项回顾性队列研究纳入了 2012 年至 2022 年期间一家医疗中心至少有一次心电图（ECG）和胸部 X 线（CXR）的 134112 例急诊科就诊，此外，一家独立的社区医院提供了 45614 例急诊科就诊作为外部验证集。我们使用初始评估数据训练了一个极端梯度提升（XGB）模型，以预测 7 天内的全因死亡率。使用 ECG 和 CXR 训练了两个深度学习模型（DLMs），以分层死亡率风险。动态分诊级别基于 XGB-分诊的输出和来自 ECG 和 CXR 的 DLM。在内部和外部验证期间，XGB-分诊模型的受试者工作特征曲线下面积（AUC）>0.866；此外，使用 ECG 和 CXR 的 DLM 的 AUC 分别为>0.862 和>0.886。与原始分诊量表相比，动态分诊量表提供了更高的 C 指数（0.914-0.920 vs. 0.827-0.843），并展示了对 5 年死亡率、30 天 ED 复诊和 30 天出院的更好预测能力。基于 AI 的风险量表为急诊科患者的死亡率风险提供了更准确和动态的分层，特别是在识别由于非典型症状而容易被忽视的患者方面。
