Heart disease is one of the most serious health problems worldwide, and early diagnosis plays a key role in reducing mortality. Traditional diagnosis methods are often time-consuming and depend heavily on medical expertise. This research presents a performance-focused approach for heart disease prediction and classification using five machine learning and deep learning models: Logistic Regression, Decision Tree, Support Vector Machine, Random Forest, and Optimized Deep Neural Network. Optimization techniques such as feature scaling, hyperparameter tuning, and regularization are applied to improve model performance. Experimental results show that the optimized deep learning model achieves better accuracy and reliability compared to traditional machine learning approaches. The proposed system can support healthcare professionals in accurate and early heart disease diagnosis.