Type-2 Fuzzy Hybrid Expert System For Diagnosis Of Degenerative Disc Diseases

Abstract

One-third of the people with an age over twenty have some signs of degenerated discs. However, in most of the patients the mere presence of degenerative discs is not a problem leading to pain, neurological compression, or other symptoms. This paper presents an interval type-2 fuzzy hybrid rule-based system to diagnose the abnormal degenerated discs where pain variables are represented by interval type-2 membership functions. For this purpose, Mamdani interval type-2 fuzzy sets are utilized in the inference engine. The main contribution of this paper is to present the interval type-2 fuzzy hybrid rule-based system, which is the combination of forward and backward chaining approach in its inference engine. Combining forward and backward chaining leads to detect the exact location of degenerated disc that shows some spinal instability. The phase of forward chaining diagnoses the severity of the degeneration based on taking history of the patient. The second phase uses backward chaining approach to find the exact location of the degenerated disc by investigating related clinical examinations. Using parametric operations for the fuzzy calculations increases the robustness of the system. The system is tested for 11 patients and the results are compared with the neurosurgeon’s diagnosis. Results indicate that the hybrid of forward and backward chaining approaches provide fast and accurate diagnosis of degenerative disc disease, and determine the necessity of taking MRI. Concluding, the proposed system could be a valuable tool in hand of the physicians in clinics and imaging centers to support diagnosis of the degenerated discs.