Machine learning-based heart attack prediction: A symptomatic heart attack prediction method and exploratory analysis

Background; Heart attack prediction is one of the serious causes morbidity in world’s population. The clinical data analysis includes a very crucial disease i.e., cardiovascular as most important sections for prediction. Data Science and machine learning (ML) can be helpful heart attacks which different risk factors like high blood pressure, cholesterol, abnormal pulse rate, diabetes, etc... considered. objective this study to optimize using ML. Methods: In paper, we are presenting learning-based (ML-HAP) method done ML approaches Support Vector Machines, Logistic Regression, Naïve Bayes XGBoost. symptoms has been collected from UCI Repository performed on methods. focus optimizing basis parameters. Results: XGBoost provided best among four. Area under curve achieved with .94 Regression .92. models identifying highly efficient, especially boosting algorithms. was evaluate accuracy, precision, recall, area curve. being trained perform optimized predictions. Conclusions: This help clinically analyzing interpretation patient scenario. Boosting algorithm promising results predict disease. It further by working associated condition.