Background and aims: We aimed to evaluate the association of epicardial adipose tissue (EAT) with coronary CT angiography (CCTA) plaque parameters on cardiovascular outcome in patients with and without diabetes mellitus. Methods: Data of 353 patients (62.9 +/- 10.4 years, 62% male), who underwent CCTA as part of their clinical workup for the evaluation of suspected or known CAD, were retrospectively analyzed. EAT volume and plaque parameters from CCTA were compared in patients with diabetes (n = 63) and without diabetes (n = 290). Follow-up was performed to record adverse cardiovascular events. The predictive value to detect adverse cardiovascular events was assessed using concordance indices (CIs) and multivariable Cox proportional hazards analysis. Results: In total, 33 events occurred after a median follow-up of 5.1 years. In patients with diabetes, EAT volume and plaque parameters were significantly higher than in patients without diabetes (all p < 0.05). A multivariable model demonstrated an incrementally improved C-index of 0.84 (95%CI 0.80-0.88) over the Framingham risk score and single measures alone. In multivariable Cox regression analysis EAT volume (Hazard ratio[HR] 1.21, p = 0.022), obstructive CAD (HR 1.18, p = 0.042), and >= 2 high-risk plaque features (HR 2.13, p = 0.031) were associated with events in patients with diabetes and obstructive CAD (HR 1.88, p = 0.017), and Agatston calcium score (HR 1.009, p = 0.039) in patients without diabetes. Conclusions: EAT, as a biomarker of inflammation, and plaque parameters, as an extent of atherosclerotic CAD, are higher in patients with diabetes and are associated with increased adverse cardiovascular outcomes. These parameters may help identify patients at high risk with need for more aggressive therapeutic and preventive care.

To evaluate the long-term prognostic value of coronary CT angiography (cCTA)-derived plaque measures and clinical parameters on major adverse cardiac events (MACE) using machine learning (ML). Datasets of 361 patients (61.9 ± 10.3 years, 65% male) with suspected coronary artery disease (CAD) who underwent cCTA were retrospectively analyzed. MACE was recorded. cCTA-derived adverse plaque features and conventional CT risk scores together with cardiovascular risk factors were provided to a ML model to predict MACE. A boosted ensemble algorithm (RUSBoost) utilizing decision trees as weak learners with repeated nested cross-validation to train and validate the model was used. Performance of the ML model was calculated using the area under the curve (AUC). MACE was observed in 31 patients (8.6%) after a median follow-up of 5.4 years. Discriminatory power was significantly higher for the ML model (AUC 0.96 [95%CI 0.93–0.98]) compared with conventional CT risk scores including Agatston calcium score (AUC 0.84 [95%CI 0.80–0.87]), segment involvement score (AUC 0.88 [95%CI 0.84–0.91]), and segment stenosis score (AUC 0.89 [95%CI 0.86–0.92], all p < 0.05). Similar results were shown for adverse plaque measures (AUCs 0.72–0.82, all p < 0.05) and clinical parameters including the Framingham risk score (AUCs 0.71–0.76, all p < 0.05). The ML model yielded significantly higher diagnostic performance compared with logistic regression analysis (AUC 0.96 vs. 0.92, p = 0.024). Integration of a ML model improves the long-term prediction of MACE when compared with conventional CT risk scores, adverse plaque measures, and clinical information. ML algorithms may improve the integration of patient’s information to enhance risk stratification. • A machine learning (ML) model portends high discriminatory power to predict major adverse cardiac events (MACE). • ML-based risk stratification shows superior diagnostic performance for MACE prediction over coronary CT angiography (cCTA)-derived risk scores or clinical parameters alone. • A ML model outperforms conventional logistic regression analysis for the prediction of MACE.

In spite of the advances in scanner technology in coronary CT angiography (CCTA), image quality is still influenced by heart rate (HR) and the consistency of the cardiac cycle. Additionally, HR is related to the diagnostic value and level of radiation exposure of CCTA (Stolzmann et al., AJR Am J Roentgenol 197:851e858, 2011; Matt et al., AJR Am J Roentgenol 189:567e573, 2007; Dewey et al., Circulation 120:867e875, 2009). The reason for pharmaceutical intervention in patients’ CCTA examinations for the assessment of coronary disease (CAD) and myocardial perfusion is the reduction of HR and the instigation of coronary vasodilatation in order to achieve maximal coronary flow. The current guidelines propose a HR of <65 bpm before imaging (Abbara et al., J Cardiovasc Comput Tomogr 3:190–204, 2009).