Cardiovascular disease plays a crucial role in the morbidity and mortality of type 2 diabetic patients. These individuals often fight with regulating their autonomic and cardiovascular systems, mainly elevating the risk of cardiovascular incidents. Considering the various complications connected to diabetes, cardiovascular autonomic neuropathy (CAN) stands out as one of the main yet poorly understood outcomes. Most research has utilized the baroreflex sensitivity index as a parameter for prediction using statistical methods. This research aims to predict the probability of autonomic dysfunction by discovering the connection between cardiovascular autonomic neuropathy and diabetes mellitus, using the baroreflex sensitivity index obtained from heart rate and blood pressure (BP) data variability in diabetic patients. With deep learning, machine learning, and considering various other factors, the prediction efficiently found out the probability of cardiovascular disease appearance in type 2 diabetic patients. The research outcome gave logistic regression and SVM accuracies of 85% and 90%, respectively, in predicting cardiovascular disease.