Support Vector Machines and Adaptive-Network-Based Fuzzy Inference Systems in medical diagnosis

In this Study, Support Vector Machines and Adaptive- Network- Based Fuzzy Inference Systems are used in diagnosing acute nephritis disease and heart disease (Data is on cardiac Single Proton Emission Computed Tomography images).Each person is classified into two groups infected and non-infected for both diseases. In medical diagnosing, accuracy plays a key role because a mistake may ultimate death or extremely harmful in long term. In this paper we propose SVM and ANFIS methods and compare them with previous results, andwe show that these results are more accurate than prior models. In this research data were obtained from UCI machine learning repository in order to diagnose diseases. SVM has been used in diagnosing acute nephritis disease and it could classify the entire test data’s. ANFIS model were used in diagnosing heart attack and it could classify 94.5% of patients.

Keywords:

adaptive network based fuzzy inference system , support vector machine , medical diagnosing , principle component analysis