Machine Learning-Based Intelligent System for Heart Disease Prediction

Late in the 20th century, heart disease began to assume the stature of the leading cause of death in the world. Hence, finding ways to notice heart diseases early on is an important step in lowering the risk factors involved and ensuring better outcomes for patients. The current paper presents a model based on machine learning for predicting heart diseases by applying Logistic Regression, Naive Bayes, and XGBoost. Various medical datasets, which include demographic patient information, clinical measurements, and historical health data, have undergone preprocessing with a series of techniques ranging from the filling in of missing data, normalization, to categorical encoding, thus ensuring the quality of the respective data. Binary classification is achieved with Logistic Regression and Naive Bayes, while XGBoost improves model accuracy and minimizes overfitting. Model performance is evaluated based on accuracy, precision, recall, Fl score, and cross-validation for reliability. This paper thus highlights the potential of machine learning technology in assisting early detection and clinical decision-making in healthcare through the use of these advanced techniques.