Prediction of Heart Stroke using Machine Learning Algorithms

Heart strokes remain a significant global health burden, emphasizing the need for early detection and preventive measures. This research investigates the application of machine learning techniques to predict the occurrence of heart strokes. A prediction model was developed using age and cholesterol levels as key criteria, leveraging a dataset of medical records with lipid profiles and demographic data. The model, trained using MATLAB’s classification learner tool, achieved an impressive accuracy rate of $\mathbf{9 5 - 9 7 \%}$. Confusion matrices and scatter plots were employed to evaluate the model’s effectiveness in differentiating between individuals at high risk and those at low risk. The results demonstrate the potential of machine learning to significantly improve predictive accuracy in clinical settings, enabling prompt intervention and reducing the overall incidence of heart strokes.