Rule based fuzzy approach for peripheral motor neuropathy (PMN) diagnosis based on NCS data

The development of artificial intelligence methodology (AIM) led to development of computer assist diagnosis systems which are based on expert medical knowledge. Medical diagnosis is a complex system as well as subjective in nature and needs expert person for interpretation of medical information. Moreover, abundance of data in database is often beyond human cognition and comprehension. It is widely pointed that the conventional diagnosis cannot sufficiently handle imprecise and vague knowledge for some real world applications, but expert system such as fuzzy model can effectively resolve/interpretate data and knowledge problems with uncertainty. This paper presents a novel fuzzy expert system (FES) for neuropathy decision support application. In this study group, 120 neuropathy patients, 4 nerves and 5 variables of each nerve were considered for analysis. 26 rules were evaluated based on medical knowledge. After the system is completely constructed, new data were encoded to linguistic variables and tested to predict the model performance. The simulation results have shown that the proposed FES can be used for medical data analysis effectively. The comparison results show that the linguistic rules extracted are competitive with or even superior to some well-known medical methods. Results are presented showing the effectiveness of the method for supporting differential diagnosis.