Prediction and risk analysis of Cardio Vascular diseases in IoHT by enhanced CHIO-based Residual and dilated gated network with Attention Mechanism

Abstract

Generally, computer networks automatically discover data based on the machine learning process. It is the execution of Artificial Intelligence (AI) without any specific program. Using both machine learning and AI, an effective optimization was done for Cardio Vascular Disease (CVD). CVD is associated with disorders that lead to hypertension and unexpected cardiac arrest. To promote good health and prevent risky situations, the Internet of Health Things (IoHT) helps to enhance the treatment's effectiveness. The most challenging task is to perform accurate heart disease prediction. Thus, a CVD prediction model is designed. At first, the needed information is collected from the benchmark dataset. After that, the pre-processing is done on the collected data using the data cleaning and scaling method. The pre-processed data are sent to the CVD prediction phase with the aid of Adaptive Residual and Dilated Long Short Term Memory with Attention Mechanism (ARDL-AM) and the parameters in this structure are optimized by the Enhanced Coronavirus Herd Immunity Optimizer (ECHIO). The obtained results from the ARDL-AM are used for the CVD prediction process. The simulations were carried out with various measures to calculate the recommended method's efficiency.