Heart Disease Prediction Analysis with Machine Learning

When early diagnosis and treatment of heart diseases becomes increasingly challenging. However, various studies and researches discovered that recent development in technologies affects the healthcare industry with the advanced machine learning techniques. A machine learning predictive model (LumenCardia) for heart-diseases based on relative parameters is the aim of this work. In this project, we had employed the dataset called Cleveland heart disease dataset, which includes 14 distinct heart disease-related factors. In this study we had applied ML techniques like Random Forest, Logistic Regression, KNN, and Decision Tree to our model. We also looked for relationships among different features in our dataset using conventional ML techniques. The outcome demonstrates that Random Forest produces predictions with more accuracy (93.18%) in less time than other machine learning algorithms. The medical professionals may find LumenCardia beneficial as a decision support system.