Turku PET Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, 20520, Turku, Finland.
Cardiac Imaging Division Alkmaar, Department of Nuclear Medicine, Northwest Clinics, Alkmaar, The Netherlands.
J Nucl Cardiol. 2020 Feb;27(1):147-155. doi: 10.1007/s12350-018-1304-x. Epub 2018 May 22.
A significant number of variables are obtained when characterizing patients suspected with myocardial ischemia or at risk of MACE. Guidelines typically use a handful of them to support further workup or therapeutic decisions. However, it is likely that the numerous available predictors maintain intrinsic complex interrelations. Machine learning (ML) offers the possibility to elucidate complex patterns within data to optimize individual patient classification. We evaluated the feasibility and performance of ML in utilizing simple accessible clinical and functional variables for the identification of patients with ischemia or an elevated risk of MACE as determined through quantitative PET myocardial perfusion reserve (MPR).
1,234 patients referred to Nitrogen-13 ammonia PET were analyzed. Demographic (4), clinical (8), and functional variables (9) were retrieved and input into a cross-validated ML workflow consisting of feature selection and modeling. Two PET-defined outcome variables were operationalized: (1) any myocardial ischemia (regional MPR < 2.0) and (2) an elevated risk of MACE (global MPR < 2.0). ROC curves were used to evaluate ML performance.
16 features were included for boosted ensemble ML. ML achieved an AUC of 0.72 and 0.71 in identifying patients with myocardial ischemia and with an elevated risk of MACE, respectively. ML performance was superior to logistic regression when the latter used the ESC guidelines risk models variables for both PET-defined labels (P < .001 and P = .01, respectively).
ML is feasible and applicable in the evaluation and utilization of simple and accessible predictors for the identification of patients who will present myocardial ischemia and an elevated risk of MACE in quantitative PET imaging.
在描述疑似心肌缺血或有发生主要不良心血管事件（MACE）风险的患者时，会获得大量变量。指南通常使用其中少数几个变量来支持进一步的检查或治疗决策。然而，许多可用的预测因素可能存在内在的复杂相互关系。机器学习（ML）提供了一种从数据中阐明复杂模式的可能性，以优化个体患者分类。我们评估了 ML 在利用简单可及的临床和功能变量识别通过氮-13 氨正电子发射断层扫描（PET）心肌灌注储备（MPR）定量检查确定存在缺血或 MACE 风险升高的患者中的可行性和性能。
分析了 1234 例因氮-13 氨 PET 而被转诊的患者。检索了人口统计学（4）、临床（8）和功能变量（9），并将其输入到一个交叉验证的 ML 工作流程中，该流程包括特征选择和建模。定义了两个 PET 结果变量：（1）任何心肌缺血（局部 MPR<2.0）和（2）MACE 风险升高（全局 MPR<2.0）。ROC 曲线用于评估 ML 性能。
ML 采用提升集成算法，纳入了 16 个特征。ML 在识别心肌缺血和 MACE 风险升高的患者方面的 AUC 分别为 0.72 和 0.71。当后者使用 ESC 指南风险模型变量进行两种 PET 定义的标签时，ML 的性能优于逻辑回归（P<0.001 和 P=0.01）。
ML 是可行的，适用于评估和利用简单和可及的预测因素，以识别在定量 PET 成像中出现心肌缺血和 MACE 风险升高的患者。
