Enhanced Heart Disease Prediction Using Advanced Machine Learning and Deep Learning Models

Abstract

Heart disease prediction is a critical area in healthcare, where accurate and timely diagnosis can lead to better patient outcomes and reduced mortality rates. This study compares the performance of various machine learning models, including Logistic Regression, Random Forest, Gradient Boosting, and Neural Networks, alongside advanced deep learning models such as Convolutional Neural Networks (CNN) and VGG16, a pre-trained deep learning architecture. The models are evaluated using precision, recall, F1-score, and accuracy, with accuracy being the primary metric for comparison. Experimental results demonstrate that while traditional machine learning models like Random Forest and Logistic Regression perform adequately, deep learning models, particularly CNN and VGG16, excel in predictive accuracy and other performance metrics. Among all models, CNN and VGG16 deliver superior results, with VGG16 slightly outperforming CNN in terms of precision and recall due to its ability to leverage pre-trained features and deeper architecture.
The findings highlight the efficacy of deep learning techniques, especially VGG16, in heart disease prediction, emphasizing their ability to capture complex patterns and improve diagnostic accuracy. This study provides valuable insights into the potential of leveraging state-of-the-art deep learning architectures for enhancing predictive models in healthcare applications, setting the stage for future real-time diagnostic tools.