We evaluated the performance of conventional (C) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride (CZT)-SPECT in a large cohort of patients with suspected or known coronary artery disease (CAD) and compared the diagnostic accuracy of the two systems using machine learning (ML) algorithms. A total of 517 consecutive patients underwent stress myocardial perfusion imaging (MPI) by both C-SPECT and CZT-SPECT. In the overall population, an excellent correlation between stress MPI data and left ventricular (LV) functional parameters measured by C-SPECT and by CZT-SPECT was observed (all < .001). ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (NN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for k-NN) was greater than that of C-SPECT (88% for RF and 53% for k-NN). MPI data and LV functional parameters obtained by CZT-SPECT are highly reproducible and provide good correlation with those obtained by C-SPECT. ML approach showed that the accuracy and sensitivity of CZT-SPECT is greater than C-SPECT in detecting CAD.

中文翻译：

---

基于机器学习的方法直接比较传统心肌灌注成像和碲化镉锌 SPECT 的诊断准确性


我们评估了传统 (C) 单光子发射计算机断层扫描 (SPECT) 和碲化镉锌 (CZT)-SPECT 在一大群疑似或已知冠状动脉疾病 (CAD) 患者中的表现，并比较了诊断准确性使用机器学习（ML）算法的两个系统。共有 517 名连续患者通过 C-SPECT 和 CZT-SPECT 接受了应激心肌灌注成像 (MPI)。在总体人群中，观察到压力 MPI 数据与 C-SPECT 和 CZT-SPECT 测量的左心室 (LV) 功能参数之间存在极好的相关性（全部 < .001）。通过实施随机森林 (RF) 和 k 最近邻 (NN) 算法进行的 ML 分析证明，CZT-SPECT 在检测 CAD 方面比 C-SPECT 具有更高的准确性。对于这两种算法，CZT-SPECT 的灵敏度（RF 为 96%，k-NN 为 60%）高于 C-SPECT（RF 为 88%，k-NN 为 53%）。通过 CZT-SPECT 获得的 MPI 数据和 LV 功能参数具有高度重复性，并且与通过 C-SPECT 获得的数据具有良好的相关性。 ML 方法表明 CZT-SPECT 在检测 CAD 方面的准确性和灵敏度高于 C-SPECT。