Center for Coronary Artery Disease (CCAD), Beijing Institute of Heart, Lung and Blood Vessel Diseases, Beijing Anzhen Hospital, Capital Medical University, 2 Anzhen Road, Chaoyang, 100029, Beijing, China.
Intern Emerg Med. 2024 Oct;19(7):1847-1857. doi: 10.1007/s11739-024-03672-x. Epub 2024 Jun 14.
This study aimed to develop several new machine learning models based on hibernating myocardium to predict the major adverse cardiac events(MACE) of ischemic left ventricular systolic dysfunction(LVSD) patients receiving either percutaneous coronary intervention(PCI) or optimal medical therapy(OMT). This study included 329 LVSD patients, who were randomly assigned to the training or validation cohort. Least absolute shrinkage and selection operator(LASSO) regression was used to identify variables associated with MACE. Subsequently, various machine learning models were established. Model performance was compared using receiver operating characteristic(ROC) curves, the Brier score(BS), and the concordance index(C-index). A total of 329 LVSD patients were retrospectively enrolled between January 2016 and December 2021. Utilizing LASSO regression analysis, five factors were selected. Based on these factors, RSF, GBM, XGBoost, Cox, and DeepSurv models were constructed. In the development and validation cohorts, the C-indices were 0.888 vs. 0.955 (RSF). The RSF model (0.991 vs. 0.982 vs. 0.980) had the highest area under the ROC curve (AUC) compared with the other models. The BS (0.077 vs. 0.095vs. 0.077) of RSF model were less than 0.25 at 12, 18, and 24 months. This study developed a novel predictive model based on RSF to predict MACE in LVSD patients who underwent either PCI or OMT.
本研究旨在开发基于冬眠心肌的几种新的机器学习模型，以预测接受经皮冠状动脉介入治疗（PCI）或最佳药物治疗（OMT）的缺血性左心室收缩功能障碍（LVSD）患者的主要不良心脏事件（MACE）。本研究纳入了 329 名 LVSD 患者，他们被随机分配到训练或验证队列中。使用最小绝对收缩和选择算子（LASSO）回归来识别与 MACE 相关的变量。随后，建立了各种机器学习模型。使用接收者操作特征（ROC）曲线、Brier 评分（BS）和一致性指数（C-index）比较模型性能。总共回顾性纳入了 2016 年 1 月至 2021 年 12 月之间的 329 名 LVSD 患者。利用 LASSO 回归分析，选择了五个因素。基于这些因素，构建了 RSF、GBM、XGBoost、Cox 和 DeepSurv 模型。在开发和验证队列中，C 指数分别为 0.888 与 0.955（RSF）。与其他模型相比，RSF 模型的 AUC 最高（0.991 与 0.982 与 0.980）。RSF 模型的 BS（0.077 与 0.095 与 0.077）在 12、18 和 24 个月时均小于 0.25。本研究基于 RSF 开发了一种新的预测模型，用于预测接受 PCI 或 OMT 的 LVSD 患者的 MACE。
