Search

AimsSymptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA).Methods and resultsThe study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ≥64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (≥50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P

Aim:The long-term prognostic benefit of coronary computed tomographic angiography (CCTA) findings of coronary artery disease (CAD) in asymptomatic populations is unknown. Methods and results:From the prospective multicentre international CONFIRM long-term study, we evaluated asymptomatic subjects without known CAD who underwent both coronary artery calcium scoring (CACS) and CCTA (n = 1226). Coronary computed tomographic angiography findings included the severity of coronary artery stenosis, plaque composition, and coronary segment location. Using the C-statistic and likelihood ratio tests, we evaluated the incremental prognostic utility of CCTA findings over a base model that included a panel of traditional risk factors (RFs) as well as CACS to predict long-term all-cause mortality. During a mean follow-up of 5.9 ± 1.2 years, 78 deaths occurred. Compared with the traditional RF alone (C-statistic 0.64), CCTA findings including coronary stenosis severity, plaque composition, and coronary segment location demonstrated improved incremental prognostic utility beyond traditional RF alone (C-statistics range 0.71-0.73, all P  0.05, for all). Conclusions:Coronary computed tomographic angiography improved prognostication of 6-year all-cause mortality beyond a set of conventional RF alone, although, no further incremental value was offered by CCTA when CCTA findings were added to a model incorporating RF and CACS.

AimsTraditional prognostic risk assessment in patients undergoing non-invasive imaging is based upon a limited selection of clinical and imaging findings. Machine learning (ML) can consider a greater number and complexity of variables. Therefore, we investigated the feasibility and accuracy of ML to predict 5-year all-cause mortality (ACM) in patients undergoing coronary computed tomographic angiography (CCTA), and compared the performance to existing clinical or CCTA metrics.Methods and resultsThe analysis included 10 030 patients with suspected coronary artery disease and 5-year follow-up from the COronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenter registry. All patients underwent CCTA as their standard of care. Twenty-five clinical and 44 CCTA parameters were evaluated, including segment stenosis score (SSS), segment involvement score (SIS), modified Duke index (DI), number of segments with non-calcified, mixed or calcified plaques, age, sex, gender, standard cardiovascular risk factors, and Framingham risk score (FRS). Machine learning involved automated feature selection by information gain ranking, model building with a boosted ensemble algorithm, and 10-fold stratified cross-validation. Seven hundred and forty-five patients died during 5-year follow-up. Machine learning exhibited a higher area-under-curve compared with the FRS or CCTA severity scores alone (SSS, SIS, DI) for predicting all-cause mortality (ML: 0.79 vs. FRS: 0.61, SSS: 0.64, SIS: 0.64, DI: 0.62; P< 0.001).ConclusionsMachine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

AimsWe evaluated coronary artery disease (CAD) extent, severity, and major adverse cardiac events (MACEs) in never, past, and current smokers undergoing coronary CT angiography (CCTA).Methods and resultsWe evaluated 9456 patients (57.1 ± 12.3 years, 55.5% male) without known CAD (1588 current smokers; 2183 past smokers who quit ≥3 months before CCTA; and 5685 never smokers). By risk-adjusted Cox proportional-hazards models, we related smoking status to MACE (all-cause death or non-fatal myocardial infarction). We further performed 1:1:1 propensity matching for 1000 in each group evaluate event risk among individuals with similar age, gender, CAD risk factors, and symptom presentation. During a mean follow-up of 2.8 ± 1.9 years, 297 MACE occurred. Compared with never smokers, current and past smokers had greater atherosclerotic burden including extent of plaque defined as segments with any plaque (2.1 ± 2.8 vs. 2.6 ± 3.2 vs. 3.1 ± 3.3, P < 0.0001) and prevalence of obstructive CAD [1-vessel disease (VD): 10.6% vs. 14.9% vs. 15.2%, P < 0.001; 2-VD: 4.4% vs. 6.1% vs. 6.2%, P = 0.001; 3-VD: 3.1% vs. 5.2% vs. 4.3%, P < 0.001]. Compared with never smokers, current smokers experienced higher MACE risk [hazard ratio (HR) 1.9, 95% confidence interval (CI) 1.4-2.6, P < 0.001], while past smokers did not (HR 1.2, 95% CI 0.8-1.6, P = 0.35). Among matched individuals, current smokers had higher MACE risk (HR 2.6, 95% CI 1.6-4.2, P < 0.001), while past smokers did not (HR 1.3, 95% CI 0.7-2.4, P = 0.39). Similar findings were observed for risk of all-cause death.ConclusionAmong patients without known CAD undergoing CCTA, current and past smokers had increased burden of atherosclerosis compared with never smokers; however, risk of MACE was heightened only in current smokers.

AimPrior evidence observed no predictive utility of coronary CT angiography (CCTA) over the coronary artery calcium score (CACS) and the Framingham risk score (FRS), among asymptomatic individuals. Whether the prognostic value of CCTA differs for asymptomatic patients, when stratified by CACS severity, remains unknown.Methods and resultsFrom a 12-centre, 6-country observational registry, 3217 asymptomatic individuals without known coronary artery disease (CAD) underwent CACS and CCTA. Individuals were categorized by CACS as: 0-10, 11-100, 101-400, 401-1000, >1000. For CCTA analysis, the number of obstructive vessels-as defined by the per-patient presence of a ≥50% luminal stenosis-was used to grade the extent and severity of CAD. The incremental prognostic value of CCTA over and above FRS was measured by the likelihood ratio (LR) χ(2), C-statistic, and continuous net reclassification improvement (NRI) for prediction, discrimination, and reclassification of all-cause mortality and non-fatal myocardial infarction. During a median follow-up of 24 months (25th-75th percentile, 17-30 months), there were 58 composite end-points. The incremental value of CCTA over FRS was demonstrated in individuals with CACS >100 (LRχ(2), 25.34; increment in C-statistic, 0.24; NRI, 0.62, all P < 0.001), but not among those with CACS ≤100 (all P > 0.05). For subgroups with CACS >100, the utility of CCTA for predicting the study end-point was evident among individuals whose CACS ranged from 101 to 400; the observed predictive benefit attenuated with increasing CACS.ConclusionCoronary CT angiography provides incremental prognostic utility for prediction of mortality and non-fatal myocardial infarction for asymptomatic individuals with moderately high CACS, but not for lower or higher CACS.