Abstract

This study concerns the emerging challenge of myocardial infarction in Iraq and aims to classify its risk using advanced statistical methodologies. Myocardial infarction is a rising health problem in Iraq attributed to variables from age to blood pressure and outdated healthcare system. Conventional risk models fail to well illustrate the complicated and nonlinear nature of the disease history; thus we use a two-stage method in this work. The important biomarkers are extracted from the data with Chaotic Dwarf Mongoose Optimization and then they are used for non-linear analysis using Bayesian Additive Regression Trees. Data were gathered, refined and analyzed from 1,319 patients at a cardiac center. The integrated BART-CDMO hybrid model showed better prediction of MI risk than individual classifiers. The hybrid model was found to be the best way to reduce the prediction error, noise and incomplete data processing. Given the robustness of the model in various sample sizes, it could be considered as a decision support instrument for health policy planning, early detection strategies, prevention and resource allocation. The paper suggests more in-depth data analysis and exploring other sociodemographic factors, as well as training healthcare software developers in advanced data science. This method may be suitable for other chronic diseases as well.