Thyroid disorder diagnosis based on Mamdani fuzzy inference system classifier

Introduction: Classification and prediction are two most important applications of statistical methods in the field of medicine. According to this note that the classical classification are provided due to the clinical symptom and  do not involve the use of specialized information and knowledge. Therefore, using a classifier that can combine all this information, is necessary. The aim of this study was to design a decision support system for classification of thyroid disorder using fuzzy if and then classifier. Materials and Methods: The data consisted of 310 patients, including 105 healthy people, 150 hypothyroidisms and 55 hyperthyroidisms, who referred to Shahid Beheshti Hospital and Imam Khomeini Clinic of Hamadan (Iran) in order to investigate the status of their thyroid disease. In this fuzzy system variable including age and BMI, as well as laboratory tests such as TSH, T4, and T3, the score of hyperthyroid and hypothyroid symptoms used as input and the output variable includes individual health status. The max-min Mamdani inference system along with center of gravity deffizifier have been used in the fuzzy toolbox of MATLAB software. Results: The fuzzy rule-based classification model had a great performance for predicting thyroid disorder in the both test and train sets. Conclusion: Fuzzy rules-based classifier by using overlapping sets, had a high potential for managing the uncertainty associated with medical diagnosis. Also, by enabling the use of linguistic variables in the decision making process and design, the interpretation of the results has improved for doctors who are not familiar with modeling concepts.