Heart disease remains a leading cause of morbidity and mortality worldwide, necessitating accurate and early diagnostic methods. This study proposes a hybrid model combining decision trees (DT) and support vector machines (SVM) to enhance heart disease classification. The hybrid DT-SVM model leverages DT's interpretability and SVM's accuracy, processing a comprehensive dataset from the UCI machine learning repository. Data preprocessing, including feature selection and scaling, ensures quality inputs for model training. The DT segments the data hierarchically, while SVM classifiers handle non-linear patterns within each segment. The model's performance, validated through k-fold cross-validation and metrics such as precision, recall, F1-score, and accuracy, demonstrates superior predictive capabilities. The hybrid approach consistently outperforms traditional models, achieving an accuracy of 98%, indicating its potential in classification to improve patient outcomes.