Enhancing Heart Attack Prediction Accuracy by Finding the Best SVM Parameter Value with Fuzzy Logic

Cardiovascular disease (CVD) remains a leading cause of mortality globally, with heart disease being a significant contributor. Early detection is crucial for timely intervention through counseling and medication, as delayed diagnosis increases patient morbidity and mortality. However, early-stage detection is challenging due to the complexity of data processing required for accurate predictions. This study employs Fuzzy Logic to optimize Support Vector Machine (SVM) parameters, enhancing the hyperplane's effectiveness and improving prediction accuracy. Utilizing the Heart Disease Classification Dataset from Kaggle, comprising 1,319 entries with eight input and one output field, the standard SVM achieved an 80% overall accuracy, with 73<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> precision for the negative class and 83 % for the positive class, completing the process in 1.362 seconds. In contrast, the SVM optimized with Fuzzy Logic parameters achieved an 89.39% overall accuracy, with 85% precision for the negative class and 92 % for the positive class, taking 1.1 seconds. This research demonstrates that Fuzzy Logic optimization significantly enhances SVM performance in heart attack prediction.