Coronary Artery Disease Consortium Research Articles

Evaluating the American Heart Association/American College of Cardiology Guideline-Recommended and Contemporary Pretest Probability Models in a Mixed Asian Cohort: The Contribution of Coronary Artery Calcium.

Most pretest probability (PTP) tools for obstructive coronary artery disease (CAD) were Western -developed. The most appropriate PTP models and the contribution of coronary artery calcium score (CACS) in Asian populations remain unknown. In a mixed Asian cohort, we compare 5 PTP models: local assessment of the heart (LAH), CAD Consortium (CAD2), risk factor-weighted clinical likelihood, the American Heart Association/American College of Cardiology and the European Society of Cardiology PTP and 3 extended versions of these models that incorporated CACS: LAH(CACS), CAD2(CACS), and the CACS-clinical likelihood. The study cohort included 771 patients referred for stable chest pain. Obstructive CAD prevalence was 27.5%. Calibration, area under the receiver-operating characteristic curves (AUC) and net reclassification index were evaluated. LAH clinical had the best calibration (χ2 5.8; P=0.12). For CACS models, LAH(CACS) showed least deviation between observed and expected cases (χ2 37.5; P<0.001). There was no difference in AUCs between the LAH clinical (AUC, 0.73 [95% CI, 0.69-0.77]), CAD2 clinical (AUC, 0.72 [95% CI, 0.68-0.76]), risk factor-weighted clinical likelihood (AUC, 0.73 [95% CI: 0.69-0.76) and European Society of Cardiology PTP (AUC, 0.71 [95% CI, 0.67-0.75]). CACS improved discrimination and reclassification of the LAH(CACS) (AUC, 0.88; net reclassification index, 0.46), CAD2(CACS) (AUC, 0.87; net reclassification index, 0.29) and CACS-CL (AUC, 0.87; net reclassification index, 0.25). In a mixed Asian cohort, Asian-derived LAH models had similar discriminatory performance but better calibration and risk categorization for clinically relevant PTP cutoffs. Incorporating CACS improved discrimination and reclassification. These results support the use of population-matched, CACS-inclusive PTP tools for the prediction of obstructive CAD.

Simplified Approach to Predicting Obstructive Coronary Disease With Integration of Coronary Calcium: Development and External Validation.

The Diamond-Forrester model was used extensively to predict obstructive coronary artery disease (CAD) but overestimates probability in current populations. Coronary artery calcium (CAC) is a useful marker of CAD, which is not routinely integrated with other features. We derived simple likelihood tables, integrating CAC with age, sex, and cardiac chest pain to predict obstructive CAD. The training population included patients from 3 multinational sites (n=2055), with 2 sites for external testing (n=3321). We determined associations between age, sex, cardiac chest pain, and CAC with the presence of obstructive CAD, defined as any stenosis ≥50% on coronary computed tomography angiography. Prediction performance was assessed using area under the receiver-operating characteristic curves (AUCs) and compared with the CAD Consortium models with and without CAC, which require detailed calculations, and the updated Diamond-Forrester model. In external testing, the proposed likelihood tables had higher AUC (0.875 [95% CI, 0.862-0.889]) than the CAD Consortium clinical+CAC score (AUC, 0.868 [95% CI, 0.855-0.881]; P=0.030) and the updated Diamond-Forrester model (AUC, 0.679 [95% CI, 0.658-0.699]; P<0.001). The calibration for the likelihood tables was better than the CAD Consortium model (Brier score, 0.116 versus 0.121; P=0.005). We have developed and externally validated simple likelihood tables to integrate CAC with age, sex, and cardiac chest pain, demonstrating improved prediction performance compared with other risk models. Our tool affords physicians with the opportunity to rapidly and easily integrate a small number of important features to estimate a patient's likelihood of obstructive CAD as an aid to clinical management.

Deep learning-based prediction for significant coronary artery stenosis on coronary computed tomography angiography in asymptomatic populations.

Although coronary computed tomography angiography (CCTA) is currently utilized as the frontline test to accurately diagnose coronary artery disease (CAD) in clinical practice, there are still debates regarding its use as a screening tool for the asymptomatic population. Using deep learning (DL), we sought to develop a prediction model for significant coronary artery stenosis on CCTA and identify the individuals who would benefit from undergoing CCTA among apparently healthy asymptomatic adults. We retrospectively reviewed 11,180 individuals who underwent CCTA as part of routine health check-ups between 2012 and 2019. The main outcome was the presence of coronary artery stenosis of ≥70% on CCTA. We developed a prediction model using machine learning (ML), including DL. Its performance was compared with pretest probabilities, including the pooled cohort equation (PCE), CAD consortium, and updated Diamond-Forrester (UDF) scores. In the cohort of 11,180 apparently healthy asymptomatic individuals (mean age 56.1 years; men 69.8%), 516 (4.6%) presented with significant coronary artery stenosis on CCTA. Among the ML methods employed, a neural network with multi-task learning (19 selected features), one of the DL methods, was selected due to its superior performance, with an area under the curve (AUC) of 0.782 and a high diagnostic accuracy of 71.6%. Our DL-based model demonstrated a better prediction than the PCE (AUC, 0.719), CAD consortium score (AUC, 0.696), and UDF score (AUC, 0.705). Age, sex, HbA1c, and HDL cholesterol were highly ranked features. Personal education and monthly income levels were also included as important features of the model. We successfully developed the neural network with multi-task learning for the detection of CCTA-derived stenosis of ≥70% in asymptomatic populations. Our findings suggest that this model may provide more precise indications for the use of CCTA as a screening tool to identify individuals at a higher risk, even in asymptomatic populations, in clinical practice.

Use of artificial intelligence to assess the risk of coronary artery disease without additional (non-invasive) testing: validation in a low-risk to intermediate-risk outpatient clinic cohort

ObjectivesPredicting the presence or absence of coronary artery disease (CAD) is clinically important. Pretest probability (PTP) and CAD consortium clinical (CAD2) model and risk scores used in the guidelines are...

Machine learning models of clinically relevant biomarkers for the prediction of stable obstructive coronary artery disease.

BackgroundIn patients with suspected obstructive coronary artery disease (CAD), evaluation using a pre-test probability model is the key element for diagnosis; however, its accuracy is controversial. This study aimed to develop machine learning (ML) models using clinically relevant biomarkers to predict the presence of stable obstructive CAD and to compare ML models with an established pre-test probability of CAD models.MethodsEight machine learning models for prediction of obstructive CAD were trained on a cohort of 1,312 patients [randomly split into the training (80%) and internal validation sets (20%)]. Twelve clinical and blood biomarker features assessed on admission were used to inform the models. We compared the best-performing ML model and established the pre-test probability of CAD (updated Diamond-Forrester and CAD consortium) models.ResultsThe CatBoost algorithm model showed the best performance (area under the receiver operating characteristics, AUROC, 0.796, and 95% confidence interval, CI, 0.740–0.853; Matthews correlation coefficient, MCC, 0.448) compared to the seven other algorithms. The CatBoost algorithm model improved risk prediction compared with the CAD consortium clinical model (AUROC 0.727; 95% CI 0.664–0.789; MCC 0.313). The accuracy of the ML model was 74.6%. Age, sex, hypertension, high-sensitivity cardiac troponin T, hemoglobin A1c, triglyceride, and high-density lipoprotein cholesterol levels contributed most to obstructive CAD prediction.ConclusionThe ML models using clinically relevant biomarkers provided high accuracy for stable obstructive CAD prediction. In real-world practice, employing such an approach could improve discrimination of patients with suspected obstructive CAD and help select appropriate non-invasive testing for ischemia.

Breast arterial calcification and epicardial adipose tissue volume, but not density are independently associated with cardiovascular risk

BackgroundMammographically detected breast arterial calcification (BAC) has been proposed as surrogate marker for coronary artery disease (CAD) in women. Epicardial adipose tissue (EAT) and peri-coronary adipose tissue (PCAT) are inflammatory fat depots linked to atherogenesis. BAC has demonstrated association with inflammation, therefore we aimed to determine the association between BAC, EAT and PCAT. MethodsSingle-centre, retrospective, cross-sectional study of women with digital mammography and coronary computed tomography angiography (CCTA). EAT and PCAT were quantitively assessed using semi-automated software. Patient demographics and cardiovascular risk factors were obtained from medical records and mammograms reviewed for BAC. Pre-test cardiovascular risk was determined with CAD Consortium Score. Chi-square, t-test and Mann-Whitney U tests were used to assess between group differences. Multivariable linear and logistic regression modelling was conducted to adjust for confounders. ResultsAmong 153 patients (age 61, SD 11) included in this study, BAC was present in 37 (24%) patients. BAC-positive patients had higher EAT volume (EATv) (110.2 mL, SD 41 mL vs 94.4 mL, SD 41 mL, p = 0.02) but this association was not significant after adjusting for cardiovascular risk factors (p = 0.26). BAC did not associate with EAT density or PCAT. BAC and EATv were strongly associated with cardiovascular risk and CAD independent of each other: CV risk (BAC OR 7.55 (3.26–18.49), p < 0.001, EATv OR 1.02 (1.01–1.03), p < 0.001), CAD presence (BAC OR 4.26 (1.39–13), p = 0.01; EATv OR 1.01 (1.0–1.03), p = 0.04). ConclusionBAC and EATv are independent predictors of CV risk and CAD, but don't independently associate with each other, the relationship confounded by shared cardiovascular risk factors. BAC doesn't appear to associate with adipose tissue density and its presence may be cumulative result of long-term exposure to CV risk factors.

Evaluating the Coronary Artery Disease Consortium Model and the Coronary Artery Calcium Score in Predicting Obstructive Coronary Artery Disease in a Symptomatic Mixed Asian Cohort.

BackgroundThe utility of a given pretest probability score in predicting obstructive coronary artery disease (CAD) is population dependent. Previous studies investigating the additive value of coronary artery calcium (CAC) on pretest probability scores were predominantly limited to Western populations. This retrospective study seeks to evaluate the CAD Consortium (CAD2) model in a mixed Asian cohort within Singapore with stable chest pain and to evaluate the incremental value of CAC in predicting obstructive CAD.Methods and ResultsPatients who underwent cardiac computed tomography and had chest pain were included. The CAD2 clinical model comprised of age, sex, symptom typicality, diabetes, hypertension, hyperlipidemia, and smoking status and was compared with the CAD2 extended model that added CAC to assess the incremental value of CAC scoring, as well as to the corresponding locally calibrated local assessment of the heart models. A total of 522 patients were analyzed (mean age 54±11 years, 43.1% female). The CAD2 clinical model obtained an area under the curve of 0.718 (95% CI, 0.668–0.767). The inclusion of CAC score improved the area under the curve to 0.896 (95% CI, 0.867–0.925) in the CAD2 models and from 0.767 (95% CI, 0.721–0.814) to 0.926 (95% CI, 0.900–0.951) in the local assessment of the heart models. The locally calibrated local assessment of the heart models showed better discriminative performance than the corresponding CAD2 models (P<0.05 for all).ConclusionsThe CAD2 model was validated in a symptomatic mixed Asian cohort and local calibration further improved performance. CAC scoring provided significant incremental value in predicting obstructive CAD.

Analysis of clinical risk models vs. clinician's assessment for prediction of coronary artery disease among predominantly female population.

Multiple risk models are used to predict the presence of obstructive coronary artery disease (CAD) in patients with chest pain. We aimed to compare the performance of these models to an experienced cardiologist's assessment utilizing coronary angiography (CA) as a reference. We prospectively enrolled patients without known CAD referred for elective CA. We assessed pretest probability of CAD using the following risk models: Diamond-Forrester (original and updated), Duke Clinical score, ACC/AHA, CAD consortium (basic and clinical) and PROMISE minimal risk tool. All patients completed self-administrative Rose angina questionnaire. Independently, an experienced cardiologist assessed the patients to provide a binary prediction of obstructive CAD prior to CA. Obstructive CAD was defined as >80% stenosis in epicardial coronary arteries by visual assessment, or fractional flow reserve <0.80 in intermediate lesions (30-80%). A total of 150 patients were recruited (100 women, 50 men). Mean age was 58 (32-78) years. Obstructive CAD was found in 31 patients (21%). The area under the curve (AUC) for all the clinical risk prediction models (except the Duke Clinical Score, AUC 0.73, P = 0.07) was significantly lower compared with the clinician's assessment (AUC 0.51-0.65 vs. 0.81, respectively, P < 0.01). The clinician's assessment had sensitivity comparable to the Duke Clinical score, which was higher than all other clinical models. There was no difference in prediction performance on the basis of sex in this predominantly female population. In stable patients with chest pain and suspected CAD, current clinical risk models which are universally based upon the characteristics of the chest pain, show suboptimal performance in predicting obstructive CAD. These findings have important clinical implications, as current appropriateness criteria for recommending CA are on the basis of these risk models.

The Predictive Value Of A Zero Calcium Score For Excluding Obstructive Coronary Artery Disease In A Symptomatic Asian Cohort

Introduction: Coronary artery calcium (CAC) is pathognomonic of coronary atherosclerosis. A CAC score of zero helps exclude obstructive coronary artery disease (CAD) in asymptomatic subjects, serving as a gatekeeper to unnecessary investigations and treatment. CAC scoring also provides incremental value to CAD risk scoring models such as the CAD Consortium model (CAD2). However, indications for CAC assessment in individuals presenting with stable chest pain are less well established. The overall aim of this study was to evaluate the incremental value of CAC scoring as well as the use of zero CAC as a negative risk marker for obstructive CAD in a symptomatic Asian population.

Predicting Coronary Artery Disease in Primary Care: Development and Validation of a Diagnostic Risk Score for Major Ethnic Groups in Southeast Asia.

Coronary artery disease (CAD) risk prediction tools are useful decision supports. Their clinical impact has not been evaluated amongst Asians in primary care. We aimed to develop and validate a diagnostic prediction model for CAD in Southeast Asians by comparing it against three existing tools. We prospectively recruited patients presenting to primary care for chest pain between July 2013 and December 2016. CAD was diagnosed at tertiary institution and adjudicated. A logistic regression model was built, with validation by resampling. We validated the Duke Clinical Score (DCS), CAD Consortium Score (CCS), and Marburg Heart Score (MHS). Discrimination and calibration quantify model performance, while net reclassification improvement and net benefit provide clinical insights. CAD prevalence was 9.5% (158 of 1658 patients). Our model included age, gender, type 2 diabetes mellitus, hypertension, smoking, chest pain type, neck radiation, Q waves, and ST-T changes. The C-statistic was 0.808 (95% CI 0.776-0.840) and 0.815 (95% CI 0.782-0.847), for model without and with ECG respectively. C-statistics for DCS, CCS-basic, CCS-clinical, and MHS were 0.795 (95% CI 0.759-0.831), 0.756 (95% CI 0.717-0.794), 0.787 (95% CI 0.752-0.823), and 0.661 (95% CI 0.621-0.701). Our model (with ECG) correctly reclassified 100% of patients when compared with DCS and CCS-clinical respectively. At 5% threshold probability, the net benefit for our model (with ECG) was 0.063. The net benefit for DCS, CCS-basic, and CCS-clinical was 0.056, 0.060, and 0.065. PRECISE (Predictive Risk scorE for CAD In Southeast Asians with chEst pain) performs well and demonstrates utility as a clinical decision support for diagnosing CAD among Southeast Asians.

Validation of the European Society of Cardiology pre-test probability model for obstructive coronary artery disease.

Estimation of pre-test probability (PTP) of disease in patients with suspected coronary artery disease (CAD) is a common challenge. Due to decreasing prevalence of obstructive CAD in patients referred for diagnostic testing, the European Society of Cardiology suggested a new PTP (2019-ESC-PTP) model. The aim of this study was to validate that model. Symptomatic patients referred for coronary computed tomography angiography (CTA) due to suspected CAD in a geographical uptake area of 3.3 million inhabitants were included. The reference standard was a combined endpoint of CTA and invasive coronary angiography (ICA) with obstructive CAD defined at ICA as a ≥50% diameter stenosis or fractional flow reserve ≤0.80 when performed. The 2019-ESC-PTP, 2013-ESC-PTP, and CAD Consortium basic PTP scores were calculated based on age, sex, and symptoms. Of the 42328 identified patients, coronary stenosis was detected in 8.8% using the combined endpoint. The 2019-ESC-PTP and CAD Consortium basic scores classified substantially more patients into the low PTP groups (PTP < 15%) than did the 2013-ESC-PTP (64% and 65% vs. 16%, P < 0.001). Using the combined endpoint as reference, calibration of the 2019-ESC-PTP model was superior to the 2013-ESC-PTP and CAD Consortium basic score. The new 2019-ESC-PTP model is well calibrated and superior to the previously recommended models in predicting obstructive stenosis detected by a combined endpoint of CTA and ICA.

Feasibility of using deep learning to detect coronary artery disease based on facial photo.

Facial features were associated with increased risk of coronary artery disease (CAD). We developed and validated a deep learning algorithm for detecting CAD based on facial photos. We conducted a multicentre cross-sectional study of patients undergoing coronary angiography or computed tomography angiography at nine Chinese sites to train and validate a deep convolutional neural network for the detection of CAD (at least one ≥50% stenosis) from patient facial photos. Between July 2017 and March 2019, 5796 patients from eight sites were consecutively enrolled and randomly divided into training (90%, n = 5216) and validation (10%, n = 580) groups for algorithm development. Between April 2019 and July 2019, 1013 patients from nine sites were enrolled in test group for algorithm test. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated using radiologist diagnosis as the reference standard. Using an operating cut point with high sensitivity, the CAD detection algorithm had sensitivity of 0.80 and specificity of 0.54 in the test group; the AUC was 0.730 (95% confidence interval, 0.699-0.761). The AUC for the algorithm was higher than that for the Diamond-Forrester model (0.730 vs. 0.623, P < 0.001) and the CAD consortium clinical score (0.730 vs. 0.652, P < 0.001). Our results suggested that a deep learning algorithm based on facial photos can assist in CAD detection in this Chinese cohort. This technique may hold promise for pre-test CAD probability assessment in outpatient clinics or CAD screening in community. Further studies to develop a clinical available tool are warranted.

Evaluation of Stress Cardiac Magnetic Resonance Imaging in Risk Reclassification of Patients With Suspected Coronary Artery Disease

The role of stress cardiac magnetic resonance (CMR) imaging in clinical decision-making by reclassification of risk across American College of Cardiology/American Heart Association guideline-recommended categories has not been established. To examine the utility of stress CMR imaging for risk reclassification in patients without a history of coronary artery disease (CAD) who presented with suspected myocardial ischemia. A retrospective, multicenter cohort study with median follow-up of 5.4 years (interquartile range, 4.6-6.9) was conducted at 13 centers across 11 US states. Participants included 1698 consecutive patients aged 35 to 85 years with 2 or more coronary risk factors but no history of CAD who presented with suspected myocardial ischemia to undergo stress CMR imaging. The study was conducted from February 18, 2019, to March 1, 2020. Cardiovascular (CV) death and nonfatal myocardial infarction (MI). Major adverse CV events (MACE) including CV death, nonfatal MI, hospitalization for heart failure or unstable angina, and late, unplanned coronary artery bypass graft surgery. Of the 1698 patients, 873 were men (51.4%); mean (SD) age was 62 (11) years, accounting for 67 CV death/nonfatal MIs and 190 MACE. Clinical models of pretest risk were constructed and patients were categorized using guideline-based categories of low (<1% per year), intermediate (1%-3% per year), and high (>3% year) risk. Stress CMR imaging provided risk reclassification across all baseline models. For CV death/nonfatal MI, adding stress CMR-assessed left ventricular ejection fraction, presence of ischemia, and late gadolinium enhancement to a model incorporating the validated CAD Consortium score, hypertension, smoking, and diabetes provided significant net reclassification improvement of 0.266 (95% CI, 0.091-0.441) and C statistic improvement of 0.086 (95% CI, 0.022-0.149). Stress CMR imaging reclassified 60.3% of patients in the intermediate pretest risk category (52.4% reclassified as low risk and 7.9% as high risk) with corresponding changes in the observed event rates of 0.6% per year for low posttest risk and 4.9% per year for high posttest risk. For MACE, stress CMR imaging further provided significant net reclassification improvement (0.361; 95% CI, 0.255-0.468) and C statistic improvement (0.092; 95% CI, 0.054-0.131), and reclassified 59.9% of patients in the intermediate pretest risk group (48.7% reclassified as low risk and 11.2% as high risk). In this multicenter cohort of patients with no history of CAD presenting with suspected myocardial ischemia, stress CMR imaging reclassified patient risk across guideline-based risk categories, beyond clinical risk factors. The findings of this study support the value of stress CMR imaging for clinical decision-making, especially in patients at intermediate risk for CV death and nonfatal MI.

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.

BackgroundMachine 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.MethodsFor 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).ResultsMean 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).ConclusionsFor 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.

A Novel Laboratory-Based Model to Predict the Presence of Obstructive Coronary Artery Disease.

Commonly used tools to assess the probability of obstructive-coronary artery disease (CAD) were derived based on Caucasian cohorts, with their performance in China is still unknown. Furthermore, most were established based on non-laboratory variables, contributing to the limited predictive ability to some extent. Thus, we developed and internally validated a laboratory-based model with data from a Chinese cohort of 8963 inpatients, with suspected stable chest pain, referred to catheter-based coronary angiography (CAG) from September 2007 to April 2019, and then compared the present model's performance with the four most commonly used prediction tools, Coronary Artery Disease Consortium 1/2 Score (CAD1/2), Duke clinical score (DCS), and Diamond-Forrester score (DF). The final model was developed by random forest method, including 8 predictors derived from 70 variables. Five-fold cross-validation was performed to evaluate the model's prediction accuracy. In the external validation set, the present model showed a superior area under the receiver-operating curve (0.816), followed by DCS (0.66), CAD2 (0.61), CAD1 (0.59) and at last DF (0.58), respectively. Furthermore, the present model correctly classified 74.4% of obstructive-CAD patients as high-risk, and correctly classified more than one third of non-obstructive-CAD patients as low-risk. The present model's net reclassification improvement (NRI) showed a significant positive reclassification over CAD1 (NRI = 0.60, P < 0.001), DF (NRI = 0.59, P < 0.001), CAD2 (NRI = 0.57, P < 0.001), and DCS (NRI = 0.43, P < 0.001). Decision curve analysis demonstrated that the present model provided a larger net benefit compared with CAD1/2, DCS, and DF. In conclusion, the novel model, using 8 laboratory and non-laboratory variables, performed well in risk stratifying patients with suspected chest pain regarding the presence of obstructive-CAD in the present Chinese cohort.

Frequency and Significance of Coronary Artery Disease and Myocardial Bridging in Patients With Hypertrophic Cardiomyopathy

The etiology of chest pain in hypertrophic cardiomyopathy (HC) is diverse and includes coronary artery disease (CAD) as well as HC-specific causes. Myocardial bridging (MB) has been associated with HC, chest pain, and accelerated atherosclerosis. We compared HC patients with age-, gender- and CAD pre-test probability-matched outpatients presenting with chest pain to investigate differences in the presence of MB and CAD using coronary computed tomography angiography (CCTA). We studied 84 HC patients who underwent CCTA and compared these with 168 matched controls (age 54 ± 11 years, 70% men, pre-test probability 12% [5% to 32%]). MB, calcium score, plaque morphology and presence and extent of CAD were assessed for each patient. Linear mixed models were used to assess differences between cases and controls. MB was more often seen in HC patients (50% vs 25%, p <0.001). Calcium score and the presence of obstructive CAD were similar in both groups (9 [0 to 225] vs 4 [0 to 82] and 18% vs 19%; p = 0.22 and p = 0.82). In the HC group, MB was associated with pathogenic DNA variants (p = 0.04), but not with the presence of chest pain (74% vs 76%, p = 0.8), nor with worse outcome (log-rank p = 0.30). In conclusion, the prevalence and extent of CAD was equal among patients with and without HC, demonstrating that pre-test risk prediction using the CAD Consortium clinical risk score performs well in HC patients. MB was twice as prevalent in the HC group compared with matched controls, but was not associated with chest pain or decreased event-free survival in these patients.

P2713A genetic risk score improves discrimination of hemodynamically obstructive coronary artery disease (CAD) beyond the CAD Consortium scores in patients at low-to-intermediate risk of CAD

Abstract Background Genetic risk scores (GRSs), based on variants identified in genome-wide association studies (GWAS), have been shown to predict risk of coronary artery disease (CAD). However, the clinical potential remains unknown. Purpose To investigate whether a GRS improves discrimination of hemodynamically obstructive CAD beyond the CAD Consortium scores and coronary artery calcium score (CACS) in patients referred for coronary computed tomography angiography (CTA). Methods We consecutively included and genotyped 1645 patients undergoing CACS scoring and coronary CTA on a suspicion of CAD. Using LDPred, a recently validated GRS was calculated as the weighted sum of the number of CAD risk variants identified from the CARDIoGRAMplusC4D GWAS meta-analysis. Patients with a ≥50% stenosis on CTA further underwent invasive coronary angiography (ICA) with fractional flow reserve (FFR). Hemodynamically obstructive CAD was defined as a visual ICA stenosis &gt;90%, FFR &lt;0.80, or a quantitative coronary analysis stenosis &gt;50% if FFR was not feasible. Discrimination was evaluated by receiver-operating characteristics. Results Median age was 57 (interquartile range 50–64) years and 799 (49%) were males. Hemodynamically obstructive CAD was present in 14 (4%) with a low GRS (&lt;20th percentile), 91 (9%) with an intermediate GRS (20th–80th percentile) and 53 (16%) with a high GRS (&gt;80th percentile) (p&lt;0.0001). Adding the GRS improved the area under the receiver-operating curve (AUC) on top of the CAD Consortium basic score (from 0.67 to 0.72, p=0.0052), and the CAD Consortium clinical score (0.70 to 0.74, p=0.0084), but not on top of the CAD Consortium clinical score + CACS (0.85 to 0.86, p=0.30). Improvement in discrimination on top of the CAD Consortium scores was predominantly driven by females ≤57 years (CAD Consortium basic score ± GRS: 0.60 to 0.78, p=0.0004; CAD Consortium clinical score ± GRS: 0.63 to 0.78, p=0.0007). The GRS did not improve discrimination in any subgroups including CACS (CAD Consortium clinical score + CACS ± GRS: all p-values &gt;0.05). Conclusion A GRS improves discrimination of hemodynamically obstructive CAD beyond CAD consortium scores, particularly in young women. However, the additive discriminative value is attenuated in models including CACS.

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

Symptom-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). The study screened 35281 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 13054 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 < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.

Comparing the Modified History, Electrocardiogram, Age, Risk Factors, and Troponin Score and Coronary Artery Disease Consortium Model for Predicting Obstructive Coronary Artery Disease and Cardiovascular Events in Patients With Acute Chest Pain.

The objective of this study was to compare the History, Electrocardiogram, Age, Risk factors, and Troponin (HEART) score and clinical coronary artery disease (CAD) consortium (CADC) model for predicting obstructive CAD (≥50% stenosis on coronary computed tomographic angiography) and 30-day major adverse cardiovascular events (MACE, composite of acute myocardial infarction, revascularization, and mortality). We studied 1981 patients with no known CAD who presented with acute chest pain and had negative initial troponin and electrocardiogram. Chest pain was classified as typical, atypical, and nonanginal and used to score the history component of the modified HEART score. The C-statistic for predicting obstructive CAD was 0.747 [95% confidence interval (CI), 0.712-0.783] for the HEART score and 0.792 (95% CI, 0.762-0.823) for the CADC model (P = 0.0005). The C-statistic for predicting 30-day MACE was 0.820 (95% CI, 0.774-0.864) for the HEART score and 0.850 (95% CI, 0.800-0.891) for the CADC model (P = 0.11). Among the 48.3% of patients for whom the CADC model predicted ≤5% probability of obstructive CAD, the observed 30-day MACE was 0.6%; among the 48.9% of patients for whom the HEART score was ≤2, the 30-day MACE was 0.6%. In conclusion, the CADC model was more effective at predicting obstructive CAD compared to the HEART score. The HEART score and CADC model were equally effective to safely identify low-risk patients by achieving <1% missed 30-day MACE.

Imaging functional stress test for stable chest pain symptoms in patients at low pretest probability of coronary artery disease: Current practice and long-term outcome.

Stress testing in patients with low pretest probability (PTP) of coronary artery disease (CAD) has become an increasing practice, potentially leading to underestimation of its true clinical value. Our aim was to describe the current use of most employed imaging functional tests and their prognostic value. We selected patients with low PTP of CAD (CAD consortium clinical score<15%) who underwent exercise or dipyridamole stress echocardiography or single photon emission computed tomography for suspected angina. Main exclusions were age<45, known CAD, and abnormal rest wall motion. Of the 2279 subjects undergoing stress test, 883 (39%) had low PTP, and 91 (10.3%) had a positive test for ischemia. After a median follow-up of 5.8years, 36 patients had events (21 died, 14 had nonfatal myocardial infarction). The percentage of events in the abnormal and normal stress test groups were similar (5 [5.5%] vs 31 [3.9%], P=ns), as the annualized event rate (0.87% vs 0.62%, P=ns). Age was the only variable associated with outcome in the regression analysis (hazard ratio 1.072, 95% CI 1.034-1.113, P<0.001). An abnormal result was not associated with worse outcome in each of the subgroups of functional tests. In our geographical area, a considerable proportion of patients undergoing imaging functional tests for stable chest pain have a low estimated PTP of CAD. Of these, 1 in 10 resulted positive for inducible ischemia. However, none of the most common imaging functional tests, single photon emission computed tomography (SPECT), and stress echocardiography offer prognostic information in these patients.