Enhanced Hybrid Framework for Detection of Cardiovascular Disease Based on Adaptive Neural Network and Fuzzy Inference System

Cardiovascular diseases (CVD) stand as the foremost cause of mortality globally. This research focuses on identifying the likelihood of cardiovascular disease with precision and promptness, aiming to enable individuals to take proactive measures to mitigate its impact on mortality rates. This study presents a novel prediction model for early detection of cardiovascular disease, combining fuzzy techniques and artificial neural networks based on knowledge. Creating a fuzzy inference system (FIS) to predict CVD early involves establishing membership functions for risk factors that impact the likelihood of developing the condition. The neural fuzzy inference system (NFIS) utilizes training data structured around the n-dimensional function. The evaluation of the suggested adaptive neural network, integrating a fuzzy inference system, demonstrated superior performance compared to conventional approaches in accuracy (0.952), specificity (0.987), precision (0.978), and sensitivity (0.989). This study seeks to enhance the effectiveness of knowledge-based systems by utilising fuzzy logic and artificial neural networks in the early detection of cardiovascular disease.