Development of a Deep Learning-Based Predictive Model for Early Detection and Risk Assessment of Cardiovascular Diseases in Patients with Diabetes Mellitus

Abstract

In recent years, medical technology has grown by leaps and bounds, resulting in the generation of an enormous amount of patient-related data, especially during clinical trials. These trials often produce information that spans multiple dimensions—covering everything from lab results to patient histories. This explosion of data has become the foundation for big data analytics in healthcare, enabling researchers and clinicians to uncover hidden patterns and risk factors behind serious conditions like cardiovascular and respiratory diseases. With the rise of intelligent systems, robots equipped with advanced analytics are increasingly supporting doctors in detecting illnesses early and more accurately, especially in complex scenarios where human observation alone might miss subtle signs.  Among the various life-threatening conditions, cardiovascular disease remains one of the leading causes of death globally. Given its widespread nature, many data-driven approaches have been explored to predict and manage its risks. In this study, we focus on how diabetes—a known contributor to cardiovascular complications—interacts with these diseases. We employ a deep learning neural network model to analyze patient data and reveal these connections. Our findings show that the model outperforms many existing methods in terms of accuracy and F1 score, demonstrating its potential to enhance early diagnosis and provide actionable insights for preventive healthcare strategies.