Find in Library

Background: The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0_HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms. Methodology: 500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0_HDL was scientifically validated using <i>seen</i> and <i>unseen</i> datasets while the reliability and statistical tests were conducted using CST along with <i>p</i>-value significance. The performance of AtheroEdge™ 3.0_HDL was evaluated by measuring the <i>p</i>-value and area-under-the-curve for both <i>seen</i> and <i>unseen</i> data. Results: The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the <i>seen</i> datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0_HDL showed less than 1% (<i>p</i>-value < 0.001) difference between <i>seen</i> and <i>unseen</i> data, complying with regulatory standards. Conclusions: The hypothesis for AtheroEdge™ 3.0_HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.