Influence of diabetes mellitus on the diagnostic performance of machine learning–based coronary CT angiography–derived fractional flow reserve: a multicenter study

• DOI: 10.1007/s00330-021-08468-7
• Publication Date: 2022-01-12T09:04:56Z
• Authors: Yi Xue; Min Wen Zheng; Yang Hou; Fan Zhou; Jian Hua Li; Yi Ning Wang; Chun Yu Liu; Chang Sheng Zhou; Jia Yin Zhang; Meng Meng Yu; Bo Zhang; Dai Min Zhang; Yan Yi; Lei Xu; Xiu Hua Hu; Guang Ming Lu; Chun Xiang Tang; Long Jiang Zhang
• Keywords: Computed Tomography Angiography; Coronary Stenosis; Coronary Artery Disease; Coronary Angiography; Coronary Vessels; Fractional Flow Reserve, Myocardial; Machine Learning; 03 medical and health sciences; 0302 clinical medicine; Predictive Value of Tests; Diabetes Mellitus; Humans; Calcium; Tomography, X-Ray Computed; Retrospective Studies

To examine the diagnostic accuracy of machine learning-based coronary CT angiography-derived fractional flow reserve (FFRCT) in diabetes mellitus (DM) patients.In total, 484 patients with suspected or known coronary artery disease from 11 Chinese medical centers were retrospectively analyzed. All patients underwent CCTA, FFRCT, and invasive FFR. The patients were further grouped into mild (25~49 %), moderate (50~69 %), and severe (≥ 70 %) according to CCTA stenosis degree and Agatston score < 400 and Agatston score ≥ 400 groups according to coronary artery calcium severity. Propensity score matching (PSM) was used to match DM (n = 112) and non-DM (n = 214) groups. Sensitivity, specificity, accuracy, and area under the curve (AUC) with 95 % confidence interval (CI) were calculated and compared.Sensitivity, specificity, accuracy, and AUC of FFRCT were 0.79, 0.96, 0.87, and 0.91 in DM patients and 0.82, 0.93, 0.89, and 0.89 in non-DM patients without significant difference (all p > 0.05) on a per-patient level. The accuracies of FFRCT had no significant difference among different coronary stenosis subgroups and between two coronary calcium subgroups (all p > 0.05) in the DM and non-DM groups. After PSM grouping, the accuracies of FFRCT were 0.88 in the DM group and 0.87 in the non-DM group without a statistical difference (p > 0.05).DM has no negative impact on the diagnostic accuracy of machine learning-based FFRCT.• ML-based FFRCT has a high discriminative accuracy of hemodynamic ischemia, which is not affected by DM. • FFRCT was superior to the CCTA alone for the detection of ischemia relevance of coronary artery stenosis in both DM and non-DM patients. • Coronary calcification had no significant effect on the diagnostic accuracy of FFRCT to detect ischemia in DM patients.