Search

This study developed an office-based cardiovascular risk calculator using a machine learning (ML) algorithm that utilized a focused carotid ultrasound. The design of this study was divided into three steps. The first step involved collecting 18 office-based biomarkers consisting of six clinical risk factors (age, sex, body mass index, systolic blood pressure, diastolic blood pressure, and smoking) and 12 carotid ultrasound image-based phenotypes. The second step consisted of the design of an ML-based cardiovascular risk calculator-called “AtheroEdge Composite Risk Score 2.0” (AECRS2.0ML) for risk stratification, considering chronic kidney disease (CKD) as the surrogate endpoint of cardiovascular disease. The last step consisted of comparing AECRS2.0ML against the currently utilized office-based CVD calculators, namely the Framingham risk score (FRS) and the World Health Organization (WHO) risk scores. A cohort of 379 Asian-Indian patients with type-2 diabetes mellitus, hypertension, and chronic kidney disease (stage 1 to 5) were recruited for this cross-sectional study. From this retrospective cohort, 758 ultrasound scan images were acquired from the far walls of the left and right common carotid arteries [mean age = 55 ± 10.8 years, 67.28% males, 91.82% diabetic, 86.54% hypertensive, and 83.11% with CKD]. The mean office-based cardiovascular risk estimates using FRS and WHO calculators were 26% and 19%, respectively. AECRS2.0ML demonstrated a better risk stratification ability having a higher area-under-the-curve against FRS and WHO by ~30% (0.871 vs. 0.669) and ~ 20% (0.871 vs. 0.727), respectively. The office-based machine-learning cardiovascular risk-stratification tool (AECRS2.0ML) shows superior performance compared to currently available conventional cardiovascular risk calculators. [ABSTRACT FROM AUTHOR]

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings. [ABSTRACT FROM AUTHOR]