Hennecken, Jasper

Abstract Background Computed tomography coronary angiography (CCTA) has emerged as a powerful non-invasive imaging modality for the evaluation of coronary artery disease (CAD), with a global trend towards a "CT-first" strategy in stable patients with suspected CAD. While overall beneficial, this approach requires a shift in resources, straining specific parts of healthcare systems. Pre-test probability (PTP) models stratify risks of obstructive CAD and are intended to result in better utilization of CCTA. However, these models show variability across subpopulations and have modest discriminatory power with low positive predictive values (PPV). Purpose This study aims to leverage explainable artificial intelligence (XAI) for optimization of PTP models. Methods Patients that underwent a CCTA for suspected CAD with a CAD-Reporting and Data System (CAD-RADS) classification and Coronary Artery Calcium Score (CACS) were included. Obstructive CAD was defined as stenosis >50% (CAD-RADS 3 or higher). Missing data was imputed. The Risk Factor Weighted Clinical Likelihood (RF-CL) model based on clinical risk factors (age, sex, type of symptoms, smoking, hypertension, dyslipidemia, diabetes and familial predisposition) was calculated. Two gradient descent-based decision tree models, "AI-ECG" and "AI-CAC" were developed. AI-ECG is built using clinical risk factors and electrocardiogram (ECG) classification. AI-CAC is built using the aforementioned features with addition of CACS. Sensitivity analysis was performed using a 15% threshold, aligning with the threshold for CCTA acquisition. Comparative analysis was performed using Python 3.10.2, with area under the curve (AUC) analysis using the DeLong test and feature importance calculation using shapely values. Preliminary results: We identified 6178 patients with a CCTA between 2022 and 2024 in the Cardiology Centers Netherlands (CCN) and included 2083 patients (mean age 57.4 ± 10.2; 48.1% male). Obstructive CAD was present in 413 (19.8%) patients. The RF-CL model was outperformed by the AI-ECG model (AUC: 0.69 vs 0.80, p<0.001) and the AI-CACS model (AUC: 0.69 vs 0.90, p<0.001). Although sensitivity increased in both the AI-ECG and AI-CACS models from 0.46 to 0.87 and 0.83 respectively, PPV increased only in the AI-CACS model (0.37 to 0.61). Most important features were CACS, age, sex, ECG classification and familial predisposition. Conclusion and Discussion Our study demonstrates that the incorporation of XAI with clinical risk factors, ECG classification and CACS improves the pre-test probability estimation of obstructive CAD. ECG classification appears to be a robust feature. Adopting these models can stratify patients at risk for obstructive CAD, enabling targeted use of CCTA, reducing unnecessary testing, and thus alleviate the burden on healthcare systems. However, further external validation is necessary to assess the model’s performance in prospective real-world settings.Sensitivity analysis feature importance

Abstract Background Coronary Computed Tomography Angiography (CCTA) is the first-line diagnostic tool for suspected stable Coronary Artery Disease (CAD) to rule out obstructive CAD and is recommended for risk stratification. Both obstructive CAD and total plaque burden on CCTA predict cardiovascular (CV) risk. Prior studies demonstrated that type 2 diabetes (T2D) patients exhibit greater plaque burden and higher CV event risk. Purpose This study evaluates whether T2D patients undergoing CCTA for stable CAD symptoms, when matched for traditional cardiovascular risk factors, have a higher prevalence of CAD and greater atherosclerotic plaque burden. Methods A total of 568 patients were included: 284 T2D patients were 1:1 propensity-matched to 284 non-T2D patients based on age, sex, and CV risk factors. All underwent diagnostic CCTA between January 2022 and November 2023. CCTA parameters included CAD-Reporting and Data System (RADS) classification, segment involvement score (SIS), coronary artery calcium (CAC) score, and plaque composition. SIS was defined as the number of segments with at least mild plaque. Coronary segmentation followed the 16-segment model (SCCT). Plaque burden was classified as P1 (mild), P2 (moderate), P3 (severe), and P4 (extensive) per CAD-RADS 2.0, based on SIS, CAC score, and the number and severity of affected vessels. Results The mean age was 60.8 ± 9.97 years (T2D) vs. 61.2 ± 9.80 years (non-T2D), with similar gender distribution (48.6% vs. 48.9% female). BMI was significantly higher in T2D patients (29.2 vs. 26.5, p < 0.05). Smoking was less frequent in T2D patients (56.0% vs. 60.9%, p = 0.03). Other CV risk factors were similar. T2D patients were more likely to use antiplatelet and lipid-lowering agents. CAD prevalence was higher in T2D patients (83.1% vs. 76.4%, p < 0.05), while obstructive CAD was not significantly higher in T2D (33.5% vs. 27.5%, p = 0.13). No significant differences were observed in 1-, 2-, or 3-vessel disease. The SIS was significantly higher in T2D patients (3.85 vs. 3.37, p = 0.03). CAC scores were higher in T2D patients (median 60 [6–369] vs. 31 [0–224]), though not statistically significant. For plaque burden classification, P2 (moderate plaque burden) was more common in non-T2D patients (23.6% vs. 15.5%, p = 0.02), while P4 (extensive plaque burden) was significantly higher in T2D patients (21.1% vs. 14.1%, p = 0.03). Conclusion When matched for cardiovascular risk factors, T2D patients more frequently exhibited CAD on CCTA, with higher SIS scores and a greater prevalence of extensive plaque burden (P4 classification). Despite greater use of preventive medication and a lower smoking prevalence in the T2D group, plaque burden remained higher in these patients. These findings emphasize the need for improved risk stratification and preventive strategies in individuals with T2D.

Abstract Background Coronary computed tomography angiography (CCTA) is a non-invasive diagnostic modality for assessing coronary artery disease (CAD), with a growing global trend favouring a "CT-first" approach. However, this strategy strains healthcare systems as demand for CCTA increases. Pre-test probability (PTP) models for obstructive CAD are used to optimize the usage of CCTA. However, these models perform inconsistently across different subpopulations and offer limited discriminatory accuracy, with low positive predictive values (PPV). This study aims to enhance the PTP models with explainable artificial intelligence (XAI) on electrocardiogram (ECG) data. Methods Patients who underwent CCTA for suspected CAD with both CAD-Reporting and Data System (CAD-RADS) classification and Coronary Artery Calcium Score (CACS) were included. Obstructive CAD was defined as CAD-RADS 3 or above. Missing values were imputed. The Risk Factor Weighted Clinical Likelihood (RF-CL) model, based on clinical variables (age, sex, symptom type, smoking, hypertension, dyslipidaemia, diabetes, and family history) was computed. Two gradient descent decision tree models, "AI-ECG" and "AI-CAC," were developed for the pilot study. AI-ECG used clinical risk factors and ECG classification as abnormal, borderline or normal, while AI-CAC further incorporated CACS. We used a cutoff value of 15%, reflecting current guidelines. Comparative analysis was performed using area under the curve (AUC) analysis, the DeLong test for statistical comparison, and feature importance using SHAP values. We intend to develop and present a model based on ECG signal data during the conference. Pilot results We identified 6 178 patients who underwent CCTA between 2022 and 2024 at the Cardiology Centers Netherlands (CCN), of which 2 083 were included (mean age 57.4 ± 10.2 years; 48.1% male). Obstructive CAD was found in 413 (19.8%) patients. The RF-CL model was outperformed by both AI-ECG (AUC: 0.69 vs. 0.80, p<0.001) and AI-CACS (AUC: 0.69 vs. 0.90, p<0.001). Sensitivity increased in both AI models, from 0.46 to 0.87 for AI-ECG and to 0.83 for AI-CACS, while PPV improved only in the AI-CACS model (from 0.37 to 0.61). Key predictive features were CACS, age, sex, ECG classification, and family history. Conclusion and Discussion Our pilot study shows that integrating XAI with clinical risk factors and ECG classification enhances PTP estimation for obstructive CAD. Implementing this model can better stratify patients at risk of obstructive CAD, support more focused CCTA use and reduce unnecessary testing. Nonetheless, further external validation is needed to assess model performance in real-world, prospective clinical settings. Additionally, models based on raw ECG signals have the potential to extract more detailed information.Reciever Operating Characteristic CurvesFeature Importance