Diabetes Diagnosis by Case-Based Reasoning and Fuzzy Logic

Abstract

In the medical field, experts' knowledge is based on experience, theoretical knowledge and rules. Case-based reasoning is a problem-solving paradigm which is based on past experiences. For this purpose, a large number of decision support applications based on CBR have been developed. Cases retrieval is often considered as the most important step of case-based reasoning. In this article, we integrate fuzzy logic and data mining to improve the response time and the accuracy of the retrieval of similar cases. The proposed Fuzzy CBR is composed of two complementary parts; the part of classification by fuzzy decision tree realized by Fispro and the part of case-based reasoning realized by the platform JColibri. The use of fuzzy logic aims to reduce the complexity of calculating the degree of similarity that can exist between diabetic patients who require different monitoring plans. The results of the proposed approach are compared with earlier methods using accuracy as metrics. The experimental results indicate that the fuzzy decision tree is very effective in improving the accuracy for diabetes classification and hence improving the retrieval step of CBR reasoning.

Fuzzy Boolean Reasoning for Diagnosis of Diabetes

“…In the third phase the test tuple is supplied to the rules to predict the class label. Benamina et al [13] combined fuzzy logic and decision tree to improve the response time and the accuracy of the retrieval of similar cases. The proposed Fuzzy case-based reasoning is composed of two complementary parts, a classification by fuzzy decision tree and a CBR part.…”

“…The process of fuzzy inference mechanism is explained in Algorithm 1. Algorithm 1 Fuzzy logic algorithm [13]:…”

“…In this process a single number represents the outcome of the fuzzy set. The final combined fuzzy conclusion is converted into a crisp value by using the centroid method [13].…”

“…Also, the human brain is able to learn and to operate in a context where uncertainty management is indispensable. In this paper, we propose a Boolean model of fuzzy reasoning for indexing the sub-plans [13], based on characteristics of the classification by inductive learning in humans [7].…”

Editor’s Note

“…Next work also intends to help clinician to diagnose an illness, diabetes, but the proposed methods are very different, based on the case-based reasoning (CBR) concept. By using a fuzzy decision tree, Benamina et al [8] integrate fuzzy logic and data mining to improve the case retrieval step in CBR. They achieve to reduce the complexity of calculating the degree of similarity that can exist between diabetic patients who require different monitoring plans.…”