Objectives This study evaluated the added predictive value of combining clinical information and myocardial perfusion single-photon emission computed tomography (SPECT) imaging (MPI) data using machine learning (ML) to predict major adverse cardiac events (MACE).

Background Traditionally, prognostication by MPI has relied on visual or quantitative analysis of images without objective consideration of the clinical data. ML permits a large number of variables to be considered in combination and at a level of complexity beyond the human clinical reader.

Methods A total of 2,619 consecutive patients (48% men; 62 ± 13 years of age) who underwent exercise (38%) or pharmacological stress (62%) with high-speed SPECT MPI were monitored for MACE. Twenty-eight clinical variables, 17 stress test variables, and 25 imaging variables (including total perfusion deficit [TPD]) were recorded. Areas under the receiver-operating characteristic curve (AUC) for MACE prediction were compared among: 1) ML with all available data (ML-combined); 2) ML with only imaging data (ML-imaging); 3) 5-point scale visual diagnosis (physician [MD] diagnosis); and 4) automated quantitative imaging analysis (stress TPD and ischemic TPD). ML involved automated variable selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross validation.

Results During follow-up (3.2 ± 0.6 years), 239 patients (9.1%) had MACE. MACE prediction was significantly higher for ML-combined than ML-imaging (AUC: 0.81 vs. 0.78; p < 0.01). ML-combined also had higher predictive accuracy compared with MD diagnosis, automated stress TPD, and automated ischemic TPD (AUC: 0.81 vs. 0.65 vs. 0.73 vs. 0.71, respectively; p < 0.01 for all). Risk reclassification for ML-combined compared with visual MD diagnosis was 26% (p < 0.001).

Conclusions ML combined with both clinical and imaging data variables was found to have high predictive accuracy for 3-year risk of MACE and was superior to existing visual or automated perfusion assessments. ML could allow integration of clinical and imaging data for personalized MACE risk computations in patients undergoing SPECT MPI.

目的本研究评估了将临床信息与心肌灌注单光子发射计算机断层扫描（SPECT）成像（MPI）数据结合使用机器学习（ML）来预测主要不良心脏事件（MACE）的附加预测价值。

背景技术传统上，MPI的预后依赖于图像的视觉或定量分析，而没有客观考虑临床数据。ML允许将大量变量组合在一起，并且其复杂程度超出了人类临床读者的水平。

方法监测总共2619名连续患者（48％男性； 62±13岁）接受运动（38％）或药理应激（62％）的高速SPECT MPI的MACE。记录了28个临床变量，17个压力测试变量和25个成像变量（包括总灌注不足[TPD]）。在以下方面比较了用于MACE预测的接收机工作特征曲线（AUC）下的面积：1）ML与所有可用数据（ML组合）；2）仅具有成像数据的ML（ML成像）；3）5点量表视觉诊断（医师[MD]诊断）；和4）自动定量成像分析（压力TPD和缺血性TPD）。ML涉及通过信息增益排名自动选择变量，使用增强的集成算法建立模型以及10倍分层交叉验证。

结果在随访期间（3.2±0.6年），有239例患者（9.1％）患有MACE。ML组合的MACE预测显着高于ML成像（AUC：0.81对0.78； p <0.01）。与MD诊断，自动应激TPD和自动缺血性TPD相比，与ML结合使用还具有更高的预测准确性（AUC：分别为0.81 vs. 0.65 vs. 0.73 vs. 0.71；所有p <0.01）。与视觉MD诊断相比，ML合并的风险重分类为26％（p <0.001）。

结论发现ML结合临床和影像数据变量对3年MACE风险具有较高的预测准确性，并且优于现有的视觉或自动灌注评估。ML可以整合临床和影像数据，以便对接受SPECT MPI的患者进行个性化MACE风险计算。