A Comprehensive Review with Comparative Analysis of Optimization-Driven Frameworks for Sustainable Heart Disease Prediction

Cardiovascular diseases (CVDs) cause over 17.9 million fatalities a year; early and precise prediction is essential for long-term healthcare systems. We conduct a review and provide a comparative analysis across algorithmic methodology, mathematical formulation, and quantitative performance with respect to sensitivity, accuracy, Area Under the Curve (AUC), specificity, F1-score, and precision. Machine learning (ML) and deep learning (DL) techniques have developed as revolutionary tools for heart disease risk stratification. In order to provide a framework for long-term heart disease prediction, our summary for the literature review aims to pinpoint the main research gaps. These results highlight the suggested synergistic fibroblast optimization with channel attention and multilayer perceptron's scientific novelty and therapeutic applicability. (SFO-CAtt-MLP) framework and provide a path forward for sustainable, AI-driven cardiology research