[A pretest model of obstructive coronary artery disease based on machine learning: from the C-Strat study].

Objective: To develop a pretest probability model of obstructive coronary artery disease with machine learning based on multi-site Chinese population data. Methods: Chinese regiStry in early deTection and Risk strAtificaTion of coronary plaques (C-Strat) study is a prospective multi-center cohort study, in which consecutive patients with suspected obstructive coronary artery disease and ≥64 detector row coronary computed tomography angioplasty (CCTA) evaluation were included. Data from the patients were randomly split into a training set (70%) and a test set (30%). More than 50% of coronary artery stenosis by CCTA was defined as positive outcome. A boosted ensemble algorithm (XGBoost), 10-fold cross-validation and Bayesian optimization were used to establish a new prediction model-CARDIACS(pretest probability model from Chinese registry in eARly Detection and rIsk stratificAtion of Coronary plaques Study), and a logistic regression was used to establish a model-LOGISTIC in training set. The test set was used for validation and comparison among CARDIACS, LOGISTIC, UDFM (updated Diamond-Forrester Model) and DFCASS(Diamond-Forrester and CASS). Results: The study population included 29 455 patients with age of (57.0±9.7) years and 44.8% women, of whom 19.1% (5 622/29 455) had obstructive coronary artery disease. For CARDIACS, the age, the reason for visit and the body mass index (BMI) were the most important predictive variables. In the independent test set, the area under the curve (AUC) of CARDIACS was 0.72 (95%CI 0.70-0.73), which was significantly superior to that of LOGISTIC (AUC 0.69, 95%CI 0.68-0.71, P=0.015), UDFM (AUC 0.64, 95%CI 0.62-0.65, P<0.001) and DFCASS (AUC 0.66, 95%CI 0.64-0.67, P<0.001), respectively. Conclusion: Based on Chinese population, the study developed a new pretest probability model--CARDIACS, which was superior to the traditional models. CARDIACS is expected to assist in the clinical decision-making for patients with stable chest pain.

[A pilot study on the noninvasive fluid hemodynamic investigation of coronary plaque].

Objective: To characterize the hemodynamic force towards coronary plaque based on noninvasive coronary computed tomographic angiography and to investigate its relationship with plaque features and stenosis severity by computational fluid dynamics. Methods: Twenty-six patients underwent invasive fractional flow reserve measurement following coronary computed tomography angiography examination from March to September 2016 were retrospectively included. Computational fluid dynamics was applied and wall shear stress (WSS) and axial plaque stress (APS), which extracted the axial component of hemodynamic stress acting on stenotic lesions, were calculated based on the results of noninvasive coronary computed tomographic angiography. Plaque analysis was performed to elucidate plaque features and relative plaque burden. The fluid dynamics distributions in lesions with different stenosis severity were investigated. Results: Thirty-one coronary plaques with satisfactory imaging quality were analyzed, there were 11 (35.5%) dominant low WSS (<1 Pa) lesion and 20 high WSS lesion (64.5%), 8(25.8%) net retrograde APS lesion and 23(74.2%) anterograde lesion. Plaque volume was (78.5±48.6) mm(3) and plaque burden was (69.1±12.1)% in the low WSS group, which was(60.5±57.3) mm(3), and(57.5±14.0)%, respectively in the high WSS group, the plaque burden was significantly higher in the low WSS group than in the high WSS group (P=0.028), while the percentage of calcified plaque, fibrotic plaque and lipid core volume were similar between the two groups (P>0.05). Plaque volume was (79.7±69.1) mm(3) and plaque burden was(68.7±13.7)% in the group with anterograde-dominant APS plaque, which was(61.7±24.9)mm(3), and(68.9±10.4)%, respectively in the net retrograde APS lesion group (P>0.05). Percentage of lipid core area was significantly higher in the anterograde lesion group than in the retrograde lesion group ((25.1±18.1)% vs.(10.8±12.7)%, P=0.049). Both WSS and APS were significant higher in the severe obstructive coronary stenosis group than in non-severe obstructive coronary stenosis group (P<0.05). Although there was no difference in WSS between functional coronary ischemia group and non-functional coronary ischemia group ( (13.3±8.7) Pa vs. (12.5±14.2) Pa, P>0.05), the distribution of APS was different between the functional coronary ischemia group and non-functional coronary ischemia group ((1 698.8±652.6) Pa vs. (981.4±787.5) Pa, P<0.05). Conclusion: WSS and APS can uniquely characterize the stenotic segment and has a strong relationship with lesion geometry. APS may be related to the necrotic core plaque and functional coronary ischemia. Clinical application of these hemodynamic and geometric indices may be helpful to assess the future risk of plaque progress and plaque rupture, which will be helpful on determining respective treatment strategy for patients with coronary artery disease.