HEART DISEASE PREDICTION USING MACHINE LEARNING ALGORITHMS

Abstract CVD(Cardio Vascular Disease) is a group of heart and blood vessel conditions. It persists as a global health predicament, making a substantial contribution to mortality rates on a worldwide scale. The identification of early signs and the evaluation of risks through the application of diverse Machine learning algorithms constitute pivotal aspects in the development of efficacious preventative measures. The objective of this study is to implement an reliable approach to detect and prevent symptoms of heart disease. We achieve this by considering risk factors such, as blood pressure, cholesterol levels, smoking habits, obesity, diabetes, family history and a sedentary lifestyle. In this research we explore machine learning algorithms. Assess the performance of the models by evaluating their effectiveness using metrics such, as accuracy, precision, recall and F1 score. The Kaggle dataset is employed to collect the necessary samples, subsequently undergoing a process of data preprocessing and optimization. The risk factors are employed as key features. The features extracted from the data are utilized to train the model, and based upon the resultant outcomes, the algorithms are able to make predictions regarding the presence of heart disease within the samples. The conclusions drawn from these findings are subsequently compared in order to determine the most effective algorithm.