Fuzzy Rule-based Classification to Build Initial Case Library for Case-based Stress Diagnosis

M.U. Ahmed, S. Begum, P. Funk, and N. Xiong (Sweden)


Case-based reasoning, fuzzy rule-based reasoning, stress, diagnosis, classification, and case library.


Case-Based Reasoning (CBR) is receiving increased interest for applications in medical decision support. Clinicians appreciate the fact that the system reasons with full medical cases, symptoms, diagnosis, actions taken and outcomes. Also for experts it is often appreciated to get a second opinion. In the initial phase of a CBR system there are often a limited number of cases available which reduces the performance of the system. If past cases are missing or very sparse in some areas the accuracy is reduced. This paper presents a fuzzy rule-based classification scheme which is introduced into the CBR system to initiate the case library, providing improved performance in the stress diagnosis task. The experimental results showed that the CBR system using the enhanced case library can correctly classify 83% of the cases, whereas previously the correctness of the classification was 61%. Consequently the proposed system has an improved performance with 22% in terms of accuracy. In terms of the discrepancy in classification compared to the expert, the goodness-of-fit value of the test results is on average 87%. Thus by employing the fuzzy rule-based classification, the new hybrid system can generate artificial cases to enhance the case library. Furthermore, it can classify new problem cases previously not classified by the system.

Important Links:

Go Back