Predicting Heart Disease Using Machine Learning

According to a recent WHO research, there is an increase in heart-related disorders, which account for 17.9 million fatalities per year. As the population expands, recognizing and treating these disorders becomes more difficult. However, technological improvements have allowed Machine Learning (ML) techniques to have a substantial impact on the healthcare sector. The goal of this study is to develop an ML model to predict cardiac illness based on a Kaggle benchmark dataset that includes 14 different metrics linked with the condition. We used a variety of machine learning approaches, including Naive Bayes, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Logistic Regression, and decision trees. Our investigation also looked at the correlations between the dataset’s distinct attributes. The findings show that K-Nearest Neighbors outperformed the other machine learning algorithms in terms of prediction accuracy and efficiency.