Clinical likelihood models calibrated against observed obstructive coronary artery disease on computed tomography angiography.

Abstract

Aims: Models predicting the likelihood of obstructive coronary artery disease (CAD) on invasive coronary angiography (ICA) exist. However, as stable patients with new-onset chest pain frequently have lower clinical likelihood and preferably undergo index testing by noninvasive tests such as coronary computed tomography angiography (CCTA), clinical likelihood models calibrated against observed obstructive CAD at CCTA are warranted. The aim was to develop CCTA-calibrated risk-factor- and coronary artery calcium-score-weighted clinical likelihood models (i.e., RF-CLCCTA and CACS-CLCCTA models, respectively).

Methods and results: Based on age, sex, symptoms and cardiovascular risk factors, an advanced machine learning algorithm utilized a training cohort (n=38,269) of symptomatic outpatients with suspected obstructive CAD to develop both a RF-CLCCTA and a CACS-CLCCTA model to predict observed obstructive CAD on CCTA. The models were validated in several cohorts (n=28,340) and compared to a currently endorsed basic pre-test probability (Basic PTP) model. For both the training and pooled validation cohort, observed obstructive CAD at CCTA was defined as >50% diameter stenosis.Observed obstructive CAD at CCTA was present in 6,443 (22.7%) patients in the pooled validation cohort. While the Basic PTP underestimated the prevalence of observed obstructive CAD at CCTA, the RF-CLCCTA and CACS-CLCCTA models showed superior calibration. Compared to the Basic PTP model, the RF-CLCCTA and CACS-CLCCTA models showed superior discrimination (area under the receiver-operating curves 0.71 (95% confidence interval (CI) 0.70-0.72) vs. 0.74 (95%CI0.73-0.75) and 0.87 (95%CI 0.86-0.87), p<0.001 for both comparisons).

Conclusions: CCTA-calibrated clinical likelihood models improve calibration and discrimination of observed obstructive CAD at CCTA.

Clinicaltrials.gov identifier: N/A.