FEATURE-BASED IMPLEMENTATION OF MACHINE LEARNING ALGORITHMS FOR CARDIOVASCULAR DISEASE PREDICTION

In eukaryotic organisms, each and every organ takes a major role in ensuring the seamless functioning of the entire system. If we consider about heart then it is treated as a vital part of every human being. Heart-associated ailments are very frequent at present so it is essential to predict such illnesses. This prognosis and prediction of coronary heart-associated illnesses require a lot of accuracy so it must be finished in an environment-friendly manner due to the fact a small mistake can motivate the death of the person. To deal with this hassle there ought to be a gadget which can predict and create consciousness about diseases. It is challenging to decide the ailment manually primarily based on signs and hazard factors. But this ought to be solved with the use of Machine mastering techniques. Artificial brain (AI) in the shape of desktop studying (ML) allows software program purposes to predict results greater precisely whilst functioning unbiased of human input. This study employs various machine learning algorithms, including K-Nearest Neighbors, Support Vector Machine, Logistic Regression, Random Forest, Decision Tree, and Naïve Bayes, to assess their accuracy in predicting cardiovascular disease and related conditions This paper makes use of the UCI repository dataset for coaching and testing including some basic parameters such as age and sex. After applying all algorithms to our data set, the experimental results concluded that the Logistic Regression model has predicted well with highest accuracy of 92% in comparison with other algorithms.