Atherosclerosis Imaging Quantitative Computed Tomography (AI-QCT) to guide referral to invasive coronary angiography in the randomized controlled CONSERVE trial.

AIMS: We compared diagnostic performance, costs, and association with major adverse cardiovascular events (MACE) of clinical coronary computed tomography angiography (CCTA) interpretation versus semiautomated approach that use artificial intelligence and machine learning for atherosclerosis imaging-quantitative computed tomography (AI-QCT) for patients being referred for nonemergent invasive coronary angiography (ICA). METHODS: CCTA data from individuals enrolled into the randomized controlled Computed Tomographic Angiography for Selective Cardiac Catheterization trial for an American College of Cardiology (ACC)/American Heart Association (AHA) guideline indication for ICA were analyzed. Site interpretation of CCTAs were compared to those analyzed by a cloud-based software (Cleerly, Inc.) that performs AI-QCT for stenosis determination, coronary vascular measurements and quantification and characterization of atherosclerotic plaque. CCTA interpretation and AI-QCT guided findings were related to MACE at 1-year follow-up. RESULTS: Seven hundred forty-seven stable patients (60 ± 12.2 years, 49% women) were included. Using AI-QCT, 9% of patients had no CAD compared with 34% for clinical CCTA interpretation. Application of AI-QCT to identify obstructive coronary stenosis at the ≥50% and ≥70% threshold would have reduced ICA by 87% and 95%, respectively. Clinical outcomes for patients without AI-QCT-identified obstructive stenosis was excellent; for 78% of patients with maximum stenosis < 50%, no cardiovascular death or acute myocardial infarction occurred. When applying an AI-QCT referral management approach to avoid ICA in patients with <50% or <70% stenosis, overall costs were reduced by 26% and 34%, respectively. CONCLUSIONS: In stable patients referred for ACC/AHA guideline-indicated nonemergent ICA, application of artificial intelligence and machine learning for AI-QCT can significantly reduce ICA rates and costs with no change in 1-year MACE.

Machine learning insight into the role of imaging and clinical variables for the prediction of obstructive coronary artery disease and revascularization: An exploratory analysis of the CONSERVE study.

BACKGROUND: Machine learning (ML) is able to extract patterns and develop algorithms to construct data-driven models. We use ML models to gain insight into the relative importance of variables to predict obstructive coronary artery disease (CAD) using the Coronary Computed Tomographic Angiography for Selective Cardiac Catheterization (CONSERVE) study, as well as to compare prediction of obstructive CAD to the CAD consortium clinical score (CAD2). We further perform ML analysis to gain insight into the role of imaging and clinical variables for revascularization. METHODS: For prediction of obstructive CAD, the entire ICA arm of the study, comprising 719 patients was used. For revascularization, 1,028 patients were randomized to invasive coronary angiography (ICA) or coronary computed tomographic angiography (CCTA). Data was randomly split into 80% training 20% test sets for building and validation. Models used extreme gradient boosting (XGBoost). RESULTS: Mean age was 60.6 ± 11.5 years and 64.3% were female. For the prediction of obstructive CAD, the AUC was significantly higher for ML at 0.779 (95% CI: 0.672-0.886) than for CAD2 (0.696 [95% CI: 0.594-0.798]) (P = 0.01). BMI, age, and angina severity were the most important variables. For revascularization, the model obtained an overall area under the receiver-operation curve (AUC) of 0.958 (95% CI = 0.933-0.983). Performance did not differ whether the imaging parameters used were from ICA (AUC 0.947, 95% CI = 0.903-0.990) or CCTA (AUC 0.941, 95% CI = 0.895-0.988) (P = 0.90). The ML model obtained sensitivity and specificity of 89.2% and 92.9%, respectively. Number of vessels with ≥70% stenosis, maximum segment stenosis severity (SSS) and body mass index (BMI) were the most important variables. Exclusion of imaging variables resulted in performance deterioration, with an AUC of 0.705 (95% CI 0.614-0.795) (P <0.0001). CONCLUSIONS: For obstructive CAD, the ML model outperformed CAD2. BMI is an important variable, although currently not included in most scores. In this ML model, imaging variables were most associated with revascularization. Imaging modality did not influence model performance. Removal of imaging variables reduced model performance.

Selective Referral Using CCTA Versus Direct Referral for Individuals Referred to Invasive Coronary Angiography for Suspected CAD: A Randomized, Controlled, Open-Label Trial.

OBJECTIVES: This study compared the safety and diagnostic yield of a selective referral strategy using coronary computed tomographic angiography (CCTA) compared with a direct referral strategy using invasive coronary angiography (ICA) as the index procedure. BACKGROUND: Among patients presenting with signs and symptoms suggestive of coronary artery disease (CAD), a sizeable proportion who are referred to ICA do not have a significant, obstructive stenosis. METHODS: In a multinational, randomized clinical trial of patients referred to ICA for nonemergent indications, a selective referral strategy was compared with a direct referral strategy. The primary endpoint was noninferiority with a multiplicative margin of 1.33 of composite major adverse cardiovascular events (blindly adjudicated death, myocardial infarction, unstable angina, stroke, urgent and/or emergent coronary revascularization or cardiac hospitalization) at a median follow-up of 1-year. RESULTS: At 22 sites, 823 subjects were randomized to a selective referral and 808 to a direct referral strategy. At 1 year, selective referral met the noninferiority margin of 1.33 (p = 0.026) with a similar event rate between the randomized arms of the trial (4.6% vs. 4.6%; hazard ratio: 0.99; 95% confidence interval: 0.66 to 1.47). Following CCTA, only 23% of the selective referral arm went on to ICA, which was a rate lower than that of the direct referral strategy. Coronary revascularization occurred less often in the selective referral group compared with the direct referral to ICA (13% vs. 18%; p < 0.001). Rates of normal ICA were 24.6% in the selective referral arm compared with 61.1% in the direct referral arm of the trial (p < 0.001). CONCLUSIONS: In stable patients with suspected CAD who are eligible for ICA, the comparable 1-year major adverse cardiovascular events rates following a selective referral and direct referral strategy suggests that both diagnostic approaches are similarly effective. In the selective referral strategy, the reduced use of ICA was associated with a greater diagnostic yield, which supported the usefulness of CCTA as an efficient and accurate method to guide decisions of ICA performance. (Coronary Computed Tomographic Angiography for Selective Cardiac Catheterization [CONSERVE]; NCT01810198).

Multicenter Evaluation Of Coronary Dual-Source CT angiography in patients with intermediate Risk of Coronary Artery Stenoses (MEDIC): study design and rationale.

BACKGROUND: The diagnostic performance of multidetector row CT to detect coronary artery stenosis has been evaluated in numerous single-center studies, with only limited data from large cohorts with low-to-intermediate likelihood of coronary disease and in multicenter trials. The Multicenter Evaluation of Coronary Dual-Source CT Angiography in Patients with Intermediate Risk of Coronary Artery Stenoses (MEDIC) trial determines the accuracy of dual-source CT (DSCT) to identify persons with at least 1 coronary artery stenosis among patients with low-to-intermediate pretest likelihood of disease. METHODS: The MEDIC trial was designed as a prospective, multicenter, international trial to evaluate the diagnostic performance of DSCT for the detection of coronary artery stenosis compared with invasive coronary angiography. The study includes 8 sites in Germany, India, Mexico, the United States, and Denmark. The study population comprises patients referred for a diagnostic coronary angiogram because of suspected coronary artery disease with an intermediate pretest likelihood as determined by sex, age, and symptoms. All evaluations are performed by blinded core laboratory readers. RESULTS: The primary outcome of the MEDIC trial is the accuracy of DSCT to identify the presence of coronary artery stenoses with a luminal diameter narrowing of 50% or more on a per-vessel basis. Secondary outcome parameters include per-patient and per-segment diagnostic accuracy for 50% stenoses and accuracy to identify stenoses of 70% or more. Furthermore, secondary outcome parameters include the influence of heart rate, Agatston score, body weight, body mass index, image quality, and diagnostic confidence on the accuracy to detect coronary artery stenoses >50% on a per-vessel basis. CONCLUSION: The results of the MEDIC trial will assess the clinical utility of coronary CT angiography in the evaluation of patients with intermediate pretest likelihood of coronary artery disease.