Improved Heart Disease Prediction Using Combined Machine Learning and Deep Neural Network Models

Abstract

Heart disease is one of the main reasons for death around the world. Detecting it early and correctly is very important for proper treatment and prevention. In this work, we introduce an improved method for predicting heart disease by combining traditional machine learning methods with deep neural networks. Our method uses ensemble techniques and advanced feature selection to identify the most important clinical features from patient data. Popular machine learning models such as Random Forest and Gradient Boosting are combined with deep learning architectures. This combination helps the system learn both simple and complex patterns in the data. We also fine-tuned the model’s parameters using hyperparameter optimization to improve accuracy and efficiency. Tests carried out on a standard heart disease dataset showed that our method gives better accuracy, precision, and recall compared to using a single model. This hybrid approach can serve as a reliable tool for doctors and healthcare professionals. It can help in diagnosing heart disease earlier and making better treatment decisions for patients.