No abstract

Background: Early and accurate diagnosis of many diseases is critical to their treatment. Today, the classification models based on fuzzy intelligent systems help the uncertainty conditions in medicine, as well as the classification of diseases. The main goal of this study is to diagnose the most common thyroid disorders, hypothyroidism, using a fuzzy rule-based expert system. Methods: In this study, the data from patients who referred to Imam Khomeini Clinic and Shahid Beheshti Hospital in Hamadan west of Iran were collected. The data contain 305 subjects in three classes which are normal, subclinical hypothyroidism and hypothyroidism. Collected variables include demographic, symptoms as well as laboratory tests. In order to the diagnosis of Thyroid disorders, a fuzzy rule-based classifier was designed. Predictive performance of this model was compared with a multinomial logistic regression model in terms of the accuracy and the area under a ROC curve (AUC) as well as sensitivity and specificity. Results: The results showed that designed fuzzy rule-based system works well in thyroid disorder prediction with about 97% accuracy. Also, the fuzzy classifier has a better performance than the logistic regression model, especially for the subclinical hypothyroidism class. Conclusions: Fuzzy rule-based classifier by utilizing overlapping sets has improved the efficiency of classification and decision-making systems. Also, by providing the possibility of using linguistic variables in the decisionmaking process, easier interpretation, can be used by doctors who are not familiar with modeling concepts.

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.