Abstract

Cardiovascular disease (CVD) is one of the leading causes of death globally, particularly among diabetic patients who are at an elevated risk of developing heart-related complications, including high blood pressure, atherosclerosis, and stroke. This study focuses on the application of deep learning algorithms to predict heart attacks by utilizing clinical biomarkers and medical images. The integration of stacked convolutional neural networks (CNN) and recurrent neural networks (RNN), optimized using the Emperor Penguin Optimizer (EPO), allows for the efficient handling of both structured and unstructured data. The results demonstrate the potential for early diagnosis and preventive care, offering new insights into personalized medical interventions.