Cardio Prognosis: Machine Learning Approaches to Heart Disease Prediction

Global mortality is high due to cardiac disease, which affects heart anatomy and function. Timely identification improves results and lowers healthcare costs. This study uses machine learning (ML) to analyze patient data risk variables and patterns to construct a heart prediction system. This approach will enhance cardiac disease prediction and reduce misdiagnosis. In general, the datasets are heterogeneous and scattered. Therefore, cardiovascular prognostic data is needed. Numerous studies have examined heart disease types, algorithms, applications, and treatments. This study uses Decision Tree, K-Nearest Neighbor, Gaussian Naive Bayes, Random Forest, Support Vector Machine, and Logistic Regression to develop heart disease prediction models. Other algorithms include pipeline, cross-validation, hyperparameter optimization, and EDA. Logistic regression, with 99% accuracy, outperforms.