Wen Jian, Zhang Tianmei, Ye Shangrong, Li Cheng, Han Ruobing, Huang Ran, Shen Bairong, Chen Anjun, Li Qinghua
Department of Neurology, Guilin Medical University Affiliated Hospital, 15 Lequn Road, Guilin, Guangxi, 541000, China.
West China Hospital, 2222 Xingchuan Road, Chengdu, Sichuan, 610212, China.
BMC Med Inform Decis Mak. 2024 Dec 18;24(1):392. doi: 10.1186/s12911-024-02767-x.
Patients with transient ischemic attack (TIA) face a significantly increased risk of stroke. However, TIA screening and early detection rates are low, especially in developing countries. This study aims to develop an inclusive and practical TIA risk prediction model using machine learning (ML) that performs well in both hospital and resource-limited clinic settings. This model is essential for initiating the first ML-enabled learning health system (LHS) unit designed for routine and equitable TIA screening and early detection across broad populations.
Employing a novel protocol, this study first standardized data from a hospital's electronic medical records (EMR) to construct inclusive TIA risk prediction ML models using a data-centric approach. Subsequently, a quantitative distribution of TIA risk factors was applied in feature engineering to reduce the number of variables for a practical ML model. This refined model initiated a TIA ML-LHS unit that is capable of continuously updating with new EMR data from hospitals and clinics. Additionally, the practical model underwent external validation using data from another hospital.
The inclusive 150-variable ML models, derived from all available EMR variables for TIA, achieved a recall of 0.868 and an accuracy of 0.886 in predicting TIA risk. Further feature engineering produced a practical XGBoost model with 20 variables, maintaining acceptable performance of 0.855 recall and 0.796 accuracy. The initialized TIA ML-LHS unit, based on the practical model, achieved performance metrics of 0.830 recall, 0.726 precision, 0.816 ROC-AUC, and 0.812 accuracy. The model also performed well in external validation, confirming its effectiveness with patient data from different clinical settings.
This study developed the first inclusive and practical TIA XGBoost model from full hospital EHR and initiated the first TIA risk prediction ML-LHS unit. This TIA model, which requires only 20 variables, enables the ML-LHS to serve not only patients in hospitals but also those in resource-limited clinics. These results have significant implications for expanding risk-based TIA screening in community and rural clinics, thereby enhancing early detection of TIA among underserved populations and improving health equity. The novel protocol used in this study is also applicable for initiating ML-LHS units for various preventable diseases, providing a new system-level approach to responsible AI development and applications.
短暂性脑缺血发作（TIA）患者面临的中风风险显著增加。然而，TIA筛查和早期检测率较低，尤其是在发展中国家。本研究旨在利用机器学习（ML）开发一种包容性强且实用的TIA风险预测模型，该模型在医院和资源有限的诊所环境中均能表现良好。此模型对于启动首个基于ML的学习健康系统（LHS）单元至关重要，该单元旨在对广泛人群进行常规且公平的TIA筛查和早期检测。
本研究采用一种新颖的方案，首先对医院电子病历（EMR）中的数据进行标准化处理，以数据为中心的方法构建包容性的TIA风险预测ML模型。随后，在特征工程中应用TIA风险因素的定量分布，以减少实用ML模型的变量数量。这个优化后的模型启动了一个TIA ML-LHS单元，该单元能够根据医院和诊所的新EMR数据持续更新。此外，使用另一家医院的数据对实用模型进行了外部验证。
从所有可用的TIA EMR变量中得出的包含150个变量的ML模型，在预测TIA风险时召回率达到0.868，准确率达到0.886。进一步的特征工程产生了一个包含20个变量的实用XGBoost模型，召回率保持在可接受的0.855，准确率为0.796。基于实用模型初始化的TIA ML-LHS单元，召回率为0.830，精确率为0.726，ROC-AUC为0.816，准确率为0.812。该模型在外部验证中也表现良好，证实了其在不同临床环境下患者数据中的有效性。
本研究从完整的医院电子健康记录中开发出首个包容性强且实用的TIA XGBoost模型，并启动了首个TIA风险预测ML-LHS单元。这个仅需20个变量的TIA模型使ML-LHS不仅能为医院中的患者服务，也能为资源有限的诊所中的患者服务。这些结果对于在社区和农村诊所扩大基于风险的TIA筛查具有重要意义，从而提高在服务不足人群中TIA的早期检测率并改善健康公平性。本研究中使用的新颖方案也适用于启动针对各种可预防疾病的ML-LHS单元，为负责任的人工智能开发和应用提供了一种新的系统级方法。
