Abstract
<jats:p>Cardio Vascular Disease is the leading cause of death globally. According to WHO, it is estimated that 17.9 million died due to CVD in 2019, representing 32% of all global deaths. The major components of the approach include most variable selection, data pre-processing, model training and compatibility with the algorithm, and validated using robust techniques. The technique is a giant step towards proactive CVD care and better patient outcomes, especially in forecasting the start and progression of heart failure. It does this by utilizing the abundance of clinical data that is already available and leveraging advances in ML technology. In this study, the authors have developed a model with the highest accuracy based on the findings from the clinical data of a private clinic that has limited constraints of data used to compare and establish a recognized projection. The goal is to enhance the predictive model's accuracy, reliability, and interpretability, facilitating early detection and prognosis of heart diseases and contributing to the advancement of healthcare technology.</jats:p>