A PREDICTIVE MODEL FOR THE DIAGNOSIS OF HEPATITIS USING FEATURE SELECTION AND ADAPTIVE NEURO FUZZY INFERENCE SYSTEM

ABSTRACT

This study focuses on using a specific technique called Adaptive Neuro Fuzzy Inference System (ANFIS) along with feature selection; chi-square, information gain and gain ratio to diagnose hepatitis.ANFIS is a powerful computational model that combines the capabilities of neural networks and fuzzy logic. It can effectively handle complex and uncertain data, making it suitable for medical diagnosis tasks like hepatitis. Feature selection is the process of selecting the most relevant and informative features from a dataset. In the context of diagnosing hepatitis, this means identifying the most important factors or variables that can help accurately predict the presence or absence of the disease. The work uses preprocessing, model training, and optimization to accurately estimate using data from UCI repository . This work explores the potential of using ANFIS and feature selection techniques to enhance the diagnosis of hepatitis, ultimately leading to more effective and timely treatment for patient The effectiveness of the ANFIS and Feature selection; chi-square, information gain and gain ratio hybrid model is closely compared to that of conventional machine learning models, such as logistics regression, Random Forest and Support Vector Machines (SVM).