Support Vector Machine for Classifying Heart Failure, Hypertension, and Normal Heart Condition

Abstract

Cardiovascular diseases, particularly heart failure and hypertension, remain among the leading causes of global mortality, underscoring the urgent need for accurate early diagnosis. This study proposes a classification model based on the Support Vector Machine (SVM) algorithm to distinguish among heart failure, hypertension, and normal heart conditions using real-world clinical data. The dataset was preprocessed through normalization and nominal-to-numerical conversion and validated by medical experts to ensure data quality. K-Fold Cross Validation (K=10) was employed to ensure model robustness and mitigate overfitting. The SVM classifier utilized a linear kernel and achieved high performance in terms of accuracy, precision, and recall. The results demonstrate the effectiveness of the proposed model in classifying multiple cardiovascular conditions with clinically relevant input features. This research contributes to the advancement of intelligent diagnostic tools and supports the integration of machine learning into clinical decision-making processes.

Keywords

• heart disease prediction
• machine learning in healthcare
• support vector machine