Machine Learning-Driven Prediction of Heart Strokes

Globally, heart attacks are a serious health concern. Timely prediction can significantly improve patient outcomes and healthcare resource allocation. This study aims to harness machine learning techniques to develop efficient predictive models for early detection of heart strokes. Research is based on a dataset created by combining different (five) datasets. The dataset encompasses patient demographics, clinical measurements, and historical medical records. Various machine learning algorithms were employed to analyze the data, including KNearest Neighbor, Logistic Regression, Support Vector Machine, Decision Tree Classifier, and Random Forest Classifier.Crossvalidation and relevant performance metrics, such as accuracy and F1-score, are employed to assess model performance. The author's goal was to develop a strong prediction model that would reliably identify those who are more likely to suffer a heart attack. The Random Forest Classifier (RFC) is the best-performing algorithm among the models tested, with an accuracy of 86.96%, precision of 85%, recall of 91.89%, and an F1 score of 88.31%. Logistic Regression is the next top performer, with an accuracy of 84.06% and an F1 score of 85.43%. However, based on the presented metrics, the Random Forest Classifier remains the most successful option. This tool has the potential to enable early interventions and preventive measures, thereby reducing the burden of heart strokes on healthcare systems and improving patient care. Limitations encompass data quality and availability, potential bias in healthcare records, and privacy concerns related to patient data.