HEART DISEASE DIAGNOSIS USING ARTIFICIAL NEURO FUZZY INFERENCE MODEL(ANFIS)

ABSTRACT

This project aims to develop an intelligent system for heart disease prediction using Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Particle Swarm Optimization (PSO). Cardiovascular disease is a leading cause of mortality worldwide, highlighting the need for improved diagnostic tools. The proposed system integrates neural networks and fuzzy logic to address the complexities and uncertainties of medical data. The ANFIS model, optimized using PSO, enhances prediction accuracy. Compared to traditional ANFIS models, the ANFIS-PSO model demonstrated superior performance. Testing on the UCI Cleveland heart disease dataset resulted in an accuracy rate of 91.25%. This demonstrates the system's potential to assist clinicians in making reliable diagnoses based on key medical attributes. Future work may involve expanding the system to diagnose other complex diseases and incorporating additional heuristic algorithms to further refine model performance.