Abstract :

Heart stroke is one of the leading causes of death and long-term disability worldwide, making early prediction and prevention critically important in modern healthcare systems. With the rapid growth of medical data and computational intelligence, machine learning techniques have become powerful tools for predicting stroke risk accurately. This study presents a comparative analysis of various machine learning approaches used for heart stroke prediction, including Logistic Regression, Decision Trees, Support Vector Machines, Random Forest, and Neural Networks. The models are evaluated using standard performance metrics such as accuracy, precision, recall, F1-score, and AUC. Data preprocessing techniques such as normalization, feature selection, and class imbalance handling are applied to improve prediction performance. The results demonstrate that ensemble-based methods outperform traditional classifiers in terms of accuracy and sensitivity. This comparative study highlights the importa