Predicting vulnerable coronary arteries: A combined radiomics-biomechanics approach.

Background And Objective: Nowadays, vulnerable coronary plaque detection from coronary computed tomography angiography (CCTA) is suboptimal, although being crucial for preventing major adverse cardiac events. Moreover, despite the suggestion of various vulnerability biomarkers, encompassing image and biomechanical factors, accurate patient stratification remains elusive, and a comprehensive approach integrating multiple markers is lacking. To this aim, this study introduces an innovative approach for assessing vulnerable coronary arteries and patients by integrating radiomics and biomechanical markers through machine learning methods.

Methods: The study included 40 patients (7 high-risk and 33 low-risk) who underwent both CCTA and coronary optical coherence tomography (OCT). The dataset comprised 49 arteries (with 167 plaques), 7 of which (with 28 plaques) identified as vulnerable by OCT. Following image preprocessing and segmentation, CCTA-based radiomic features were extracted and a finite element analysis was performed to compute the biomechanical features. A novel machine learning pipeline was implemented to stratify coronary arteries and patients. For each stratification task, three independent predictive models were developed: a radiomic, a biomechanical and a combined radiomic-biomechanical model. Both k-nearest neighbors (KNN) and decision tree (DT) classifiers were considered.

Results: The best radiomic model (KNN) detected all 7 vulnerable arteries and patients and was associated with a balanced accuracy of 0.86 (sensitivity=1, specificity=0.71) for the artery model and of 0.83 (sensitivity=1, specificity=0.67) for the patient model. The best biomechanical model (DT) detected 6 over 7 vulnerable arteries and patients and remarkably increased the specificity, resulting in a balanced accuracy of 0.89 (sensitivity=0.86, specificity=0.93) for the artery model and of 0.88 (sensitivity=0.86, specificity=0.91) for the patient model. Notably, the combined approach optimized the performance, with an increase in the balance accuracy up to 0.94 for the artery model and up to 0.92 for the patient model, being associated with sensitivity=1 and high specificity (0.88 and 0.85 for artery and patient models, respectively).

Conclusion: This investigation highlights the promise of radio-mechanical coronary artery phenotyping for patient stratification. If confirmed from larger studies, our approach enables a more personalized management of the disease, with the early identification of high-risk individuals and the reduction of unnecessary interventions for low-risk individuals.