Interpretable Classifier of Diabetes Disease

Abstract

Interpretability represents the most important driving force behind the implementation of fuzzy-based classifiers for medical application problems. The expert should be able to understand the classifier and to evaluate its results. The main purposes in this work is the application of a new method based on FCM and ANFIS to diagnose the diabetes diseases by using a reduced number of fuzzy rules with relatively small number of linguistic labels, removing the similarity of the membership functions, preserving the meaning of the linguistic labels (interpretability), and in same time improving the classification performances. Experimental results show that the proposed approach FCM-ANFIS can get high accuracy with fewer rules. On the contrary, by using ANFIS more rules are needed to get a lower accuracy. Moreover the features projected partition in ANFIS is ambiguous and cannot preserve the meaning of the linguistic labels. The best number of the rules is a trade-off between the accuracy and the rules number, also with a minimum of clusters (c=2) and just two fuzzy rules, FCM-ANFIS approach has given the best results with CC = 83.85%, Se = 82.05% and Sp = 84.62% comparing to the other cases.