Juang Wang-Chuan, Cai Zheng-Xun, Chen Chia-Mei, You Zhi-Hong
Quality Management Center, Kaohsiung Veterans General Hospital, No.386, Dazhong 1st Rd., Zuoying Dist., Kaohsiung, 813414, Taiwan, 886 7-342-2121 ext 4191.
Department of Business Management, College of Management, National Sun Yat-sen University, Kaohsiung, Taiwan.
JMIR AI. 2025 Aug 7;4:e74053. doi: 10.2196/74053.
Overcrowded emergency rooms might degrade the quality of care and overload the clinic staff. Assessing unscheduled return visits (URVs) to the emergency department (ED) is a quality assurance procedure to identify ED-discharged patients with a high likelihood of bounce-back, to ensure patient safety, and ultimately to reduce medical costs by decreasing the frequency of URVs. The field of machine learning (ML) has evolved considerably in the past decades, and many ML applications have been deployed in various contexts.
This study aims to develop an ML-assisted framework that identifies high-risk patients who may revisit the ED within 72 hours after the initial visit. Furthermore, this study evaluates different ML models, feature sets, and feature encoding methods in order to build an effective prediction model.
This study proposes an ML-assisted system that extracts the features from both structured and unstructured medical data to predict patients who are likely to revisit the ED, where the structured data includes patients' electronic health records, and the unstructured data is their medical notes (subjective, objective, assessment, and plan). A 5-year dataset consisting of 184,687 ED visits, along with 324,111 historical electronic health records and the associated medical notes, was obtained from Kaohsiung Veterans General Hospital, a tertiary medical center in Taiwan, to evaluate the proposed system.
The evaluation results indicate that incorporating convolutional neural network-based feature extraction from unstructured ED physician narrative notes, combined with structured vital signs and demographic data, significantly enhances predictive performance. The proposed approach achieves an area under the receiver operating characteristic curve of 0.705 and a recall of 0.718, demonstrating its effectiveness in predicting URVs. These findings highlight the potential of integrating structured and unstructured clinical data to improve predictive accuracy in this context.
The study demonstrates that an ML-assisted framework may be applied as a decision support tool to assist ED clinicians in identifying revisiting patients, although the model's performance may not be sufficient for clinic implementation. Given the improvement in the area under the receiver operating characteristic curve, the proposed framework should be further explored as a workable decision support tool to pinpoint ED patients with a high risk of revisit and provide them with appropriate and timely care.
急诊室人满为患可能会降低医疗质量，并使诊所工作人员负担过重。评估急诊科（ED）的非计划复诊（URV）是一种质量保证程序，用于识别出院后很可能再次就诊的患者，以确保患者安全，并最终通过减少URV的频率来降低医疗成本。在过去几十年中，机器学习（ML）领域有了很大发展，许多ML应用已在各种场景中得到部署。
本研究旨在开发一个ML辅助框架，以识别初次就诊后72小时内可能再次前往急诊科就诊的高风险患者。此外，本研究评估不同的ML模型、特征集和特征编码方法，以构建一个有效的预测模型。
本研究提出了一个ML辅助系统，该系统从结构化和非结构化医疗数据中提取特征，以预测可能再次前往急诊科就诊的患者，其中结构化数据包括患者的电子健康记录，非结构化数据是他们的病历（主观、客观、评估和计划）。从台湾一家三级医疗中心高雄荣民总医院获取了一个5年的数据集，其中包括184,687次急诊就诊，以及324,111份历史电子健康记录和相关病历，以评估所提出的系统。
评估结果表明，将基于卷积神经网络的非结构化ED医生叙述性病历特征提取与结构化生命体征和人口统计学数据相结合，可显著提高预测性能。所提出的方法在受试者工作特征曲线下的面积为0.705，召回率为0.718，证明了其在预测URV方面的有效性。这些发现凸显了在这种情况下整合结构化和非结构化临床数据以提高预测准确性的潜力。
该研究表明，一个ML辅助框架可作为一种决策支持工具，协助ED临床医生识别复诊患者，尽管该模型的性能可能不足以在临床中实施。鉴于受试者工作特征曲线下面积有所改善，应进一步探索所提出的框架，作为一种可行的决策支持工具，以确定有高复诊风险的ED患者，并为他们提供适当和及时的护理。
