Search

Aims Coronary computed tomography angiography (CCTA) and coronary artery calcium score (CACS) have prognostic value for coronary artery disease (CAD) events beyond traditional risk assessment. Age is a risk factor with very high weight and little is known regarding the incremental value of CCTA over CAC for predicting cardiac events in older adults. Methods and results Of 27 125 individuals undergoing CCTA, a total of 3145 asymptomatic adults were identified. This study sample was categorized according to tertiles of age (cut-off points: 52 and 62 years). CAD severity was classified as 0, 1-49, and ≥50% maximal stenosis in CCTA, and further categorized according to number of vessels ≥50% stenosis. The Framingham 10-year risk score (FRS) and CACS were employed as major covariates. Major adverse cardiovascular events (MACE) were defined as a composite of all-cause death or non-fatal MI. During a median follow-up of 26 months (interquartile range: 18-41 months), 59 (1.9%) MACE occurred. For patients in the top age tertile, CCTA improved discrimination beyond a model included FRS and CACS (C-statistic: 0.75 vs. 0.70, P-value = 0.015). Likewise, the addition of CCTA improved category-free net reclassification (cNRI) of MACE in patients within the highest age tertile (e.g. cNRI = 0.75; proportion of events/non-events reclassified were 50 and 25%, respectively; P-value <0.05, all). CCTA displayed no incremental benefit beyond FRS and CACS for prediction of MACE in the lower age tertiles. Conclusion CCTA provides added prognostic value beyond cardiac risk factors and CACS for the prediction of MACE in asymptomatic older adults.

__Aims__ Traditional 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 results__ The 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). __Conclusions__ Machine learning combining clinical and CCTA data was found to predict 5-year ACM significantly better than existing clinical or CCTA metrics alone.

__Background:__ Non-obstructive coronary artery disease (CAD) identified by coronary computed tomography angiography (CCTA) demonstrated prognostic value. CT-adapted Leaman score (CT-LeSc) showed to improve the prognostic stratification. Aim of the study was to evaluate the capability of CT-LeSc to assess long-term prognosis of patients with non-obstructive (CAD). __Methods:__ From 17 centers, we enrolled 2402 patients without prior CAD history who underwent CCTA that showed non-obstructive CAD and provided complete information on plaque composition. Patients were divided into a group without CAD and a group with non-obstructive CAD (<. 50% stenosis). Segment-involvement score (SIS) and CT-LeSc were calculated. Outcomes were non-fatal myocardial infarction (MI) and the combined end-point of MI and all-cause mortality. __Results:__ Patient mean age was 56. ±. 12. years. At follow-up (mean 59.8. ±. 13.9. months), 183 events occurred (53 MI, 99 all-cause deaths and 31 late revascularizations). CT-LeSc was the only multivariate predictor of MI (HRs 2.84 and 2.98 in two models with Framingham and risk factors, respectively) and of MI plus all-cause mortality (HR 2.48 and 1.94 in two models with Framingham and risk factors, respectively). This was confirmed by a net reclassification analysis confirming that the CT-LeSc was able to correctly reclassify a significant proportion of patients (cNRI 0.28 and 0.23 for MI and MI plus all-cause mortality, respectively) vs. baseline model, whereas SIS did not. __Conclusion:__ CT-LeSc is an independent predictor of major acute cardiac events, improving prognostic stratification of patients with non-obstructive CAD.

__Background__ Left ventricular (LV) volumetric and functional parameters measured with cardiac computed tomography (cardiac CT) augment risk prediction and discrimination for future mortality. Gender- and age-specific standard values for LV dimensions and systolic function obtained by 64-slice cardiac CT are lacking __Methods and results __ 1155 patients from the Coronary CT Angiography EvaluatioN For Clinical Outcomes: An InteRnational Multicenterregistry (54.5% males, mean age 53.1 + 12.4 years, range: 18 – 92 years) without known coronary artery disease (CAD), structural heart disease, diabetes, or hypertension who underwent cardiac CT for various indications were categorized according to age and sex. A cardiac CT data acquisition protocol was used that allowed volumetric measuring of LV function. Image interpretation was performed at each site. Patients with significant CAD (.50% stenosis) on cardiac CT were excluded from the analysis. Overall, mean left ventricular ejection fraction (LVEF) was higher in women when compared with men (66.6 + 7.7% vs. 64.6 + 8.1%, P, 0.001). This gender-difference in overall LVEF was caused by a significantly higher LVEF in women ≥70 years when compared with men ≥70 years (69.95 + 8.89% vs. 65.50 + 9.42%, P ¼ 0.004). Accordingly, a significant increase in LVEF was observed with age (P ¼ 0.005 for males and P, 0.001 for females), which was more pronounced in females (5.21%) than in males (2.6%). LV end-diastolic volume decreased in females from 122.48+27.87 (,40 years) to 95.56+23.17 (.70 years; P, 0.001) and in males from 155.22+35.07 (,40 years) to 130.26+27.18 (.70 years; P, 0.001). __Conclusion__ Our findings indicate that the LV undergoes a lifelong remodelling and highlight the need for age and gender adjusted reference values.