Performance of XG Boost over other ML models for Prediction of CVD

Cardiovascular Disease (CVD), the world’s largest cause of sickness, affects millions of individuals annually, particularly in low- and middle-income countries. Early detection of CVD is crucial since conventional diagnostic methods usually lead to incorrect diagnoses and postponed treatment, increasing healthcare expenses and adversely influencing patient outcomes. This study explores the transformative potential of artificial intelligence, specifically machine learning algorithms, to increase the accuracy and efficacy of CVD diagnosis. To improve early CVD diagnosis, this study recommends utilizing a few machine learning methods. More than 32,000 records with attributes like age, sex, BMI, stroke, mental health, etc. are included in this sizable Kaggle dataset. Compared to all other algorithms, XGBoost performed competitively, with $\mathbf{9 4 . 1 \%}$ accuracy and $88.6 \%$ precision. The comparison illustrates the benefits of this strategy and the significance of these advancements in promoting early diagnosis and customized treatment regimens. Finally, by improving prediction skills, the results show how machine learning may transform the diagnosis of CVD and enhance healthcare outcomes.