Predicting Heart Diseases Using Machine Learning and Different Data Classification Techniques

Predicting Heart Diseases Using Machine Learning and Different Data Classification Techniques

C. Vamshi Kumar1, G. Manasa 2, P. Saraswathi3, Mrs. M.V Anjana Devi4

1,2,3 UG Scholars, 4Associate Professor

1,2,3,4 Department of CSE[Artificial Intelligence & Machine Learning],

1,2,3,4 Guru Nanak Institutions Technical Campus, Hyderabad, Telangana, India

Abstract - The goal of this study is to advance early detection of heart disease through a data-oriented strategy that employs machine-learning algorithms and various data classification techniques. There is a greater awareness globally around managing cardiovascular disease as we strive to achieve accurate and precise diagnosis within the parameters of time in clinical practice. In this study we explore a number of supervised learning methods such as Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Gradient Boosting for prediction of heart disease with clinical and demographic data. The Cleveland Heart Disease dataset was used for much of the study. There was an extensive preprocessing phase including data normalization, handling missing values, and selection of features. Each model was evaluated on standard metrics that included accuracy, precision, recall, F1 score, and ROC AUC. The results reveal that Random Forest and Gradient Boosting ensemble models outperform all individual classifiers, but data also supports the hypothesis that ensemble techniques elevate performance across all metrics examined .

Key Words: Heart Disease Prediction, Machine Learning, Data Classification, Ensemble Methods, Random Forest