Improving the Prediction rate of Diabetes Diagnosis Using Fuzzy, Neural Network, Case Based (FNC) approach

In today's world the diabetes mellitus has become a major health problem among the people of all ages. Most of the researchers have proposed different systems to diagnose diabetes, in spite of which the accuracy of the prediction rate of diabetes is not so significant. Most of the techniques suggested were to detect diabetes associated with the parts of the body such as eye, heart or legs. All the developed systems aimed to identify diabetes by increasing the accuracy of the prediction rate but fail to do so in most of the cases as there were some issues that had not been discussed. The existing systems had number of drawbacks like some were only concentrated for women and who were less than 21 years old [5], some gave greater accuracy if only one data set was used [6], some needed dataset of very good quality [12], some needed to standardize the ontology [10] and some even failed to show the performance of the developed systems [7]. So there is an need to develop a diabetes diagnosis system that improves the accuracy of the prediction rate by considering all the factors into account. This paper presents a novel approach for diagnosis of diabetes which has two stages to predict the diabetes status. The initial prediction stage adopts two computational intelligence and knowledge engineering techniques such as fuzzy logic (F), neural network (N) and case based reasoning (C) as an individual approach (FCN). The final prediction stage applies rule based algorithm to the values obtained from the initial stage. The benefit of applying these stages is that the accuracy of prediction rate will be higher when compared to using only the initial prediction stage done by most of the suggested systems for predicting the occurrence of diabetes mellitus. (c) 2012 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Noorul Islam Centre for Higher Education