Cardiology Department, Faculty of Medicine, Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia.
Cardiac Vascular and Lung Research Institute, Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia.
Sci Rep. 2024 May 29;14(1):12378. doi: 10.1038/s41598-024-61151-x.
The accurate prediction of in-hospital mortality in Asian women after ST-Elevation Myocardial Infarction (STEMI) remains a crucial issue in medical research. Existing models frequently neglect this demographic's particular attributes, resulting in poor treatment outcomes. This study aims to improve the prediction of in-hospital mortality in multi-ethnic Asian women with STEMI by employing both base and ensemble machine learning (ML) models. We centred on the development of demographic-specific models using data from the Malaysian National Cardiovascular Disease Database spanning 2006 to 2016. Through a careful iterative feature selection approach that included feature importance and sequential backward elimination, significant variables such as systolic blood pressure, Killip class, fasting blood glucose, beta-blockers, angiotensin-converting enzyme inhibitors (ACE), and oral hypoglycemic medications were identified. The findings of our study revealed that ML models with selected features outperformed the conventional Thrombolysis in Myocardial Infarction (TIMI) Risk score, with area under the curve (AUC) ranging from 0.60 to 0.93 versus TIMI's AUC of 0.81. Remarkably, our best-performing ensemble ML model was surpassed by the base ML model, support vector machine (SVM) Linear with SVM selected features (AUC: 0.93, CI: 0.89-0.98 versus AUC: 0.91, CI: 0.87-0.96). Furthermore, the women-specific model outperformed a non-gender-specific STEMI model (AUC: 0.92, CI: 0.87-0.97). Our findings demonstrate the value of women-specific ML models over standard approaches, emphasizing the importance of continued testing and validation to improve clinical care for women with STEMI.
在亚洲女性 ST 段抬高型心肌梗死（STEMI）后院内死亡率的准确预测仍然是医学研究中的一个关键问题。现有的模型经常忽略这一人群的特殊属性，导致治疗效果不佳。本研究旨在通过使用基础和集成机器学习（ML）模型来提高多民族亚洲女性 STEMI 患者的院内死亡率预测能力。我们专注于使用 2006 年至 2016 年期间马来西亚国家心血管疾病数据库的数据开发特定于人口统计学的模型。通过仔细的迭代特征选择方法，包括特征重要性和顺序后向消除，确定了收缩压、Killip 分级、空腹血糖、β受体阻滞剂、血管紧张素转换酶抑制剂（ACE）和口服降糖药等显著变量。我们的研究结果表明，具有选定特征的 ML 模型优于传统的心肌梗死溶栓治疗（TIMI）风险评分，曲线下面积（AUC）范围为 0.60 至 0.93，而 TIMI 的 AUC 为 0.81。值得注意的是，我们表现最好的集成 ML 模型被基础 ML 模型支持向量机（SVM）线性模型超越，该模型选择了 SVM 特征（AUC：0.93，CI：0.89-0.98 与 AUC：0.91，CI：0.87-0.96）。此外，女性特定模型优于非性别特定的 STEMI 模型（AUC：0.92，CI：0.87-0.97）。我们的研究结果表明，女性特定的 ML 模型优于标准方法，强调了继续测试和验证以改善 STEMI 女性的临床护理的重要性。
