A Rule Extractor for Diagnosing the Type 2 Diabetes Using a Self-organizing Genetic Algorithm

Introduction: Constructing medical decision support models to automatically extract knowledge from data helps physicians in early diagnosis of disease. Interpretability of the inferential rules of these models is a key indicator in determining their performance in order to understand how they make decisions, and increase the reliability of their output. Methods: In this study, an automated hybrid rule extraction model is proposed, utilizing the interpretability of fuzzy rules and the ability of the genetic algorithm (GA) to construct rules. A self-organizing chromosomal structure is used to eliminate the complexity of selecting GA operators, and to facilitate re-implementation of the model in other applications. In order to evaluate the model, PIMA Diabetes dataset including 768 records and 9 variables was used. Results: The accuracy of the proposed model on PIMA dataset was 79.05%. This accuracy is obtained by two fuzzy rules, each of which contains only two variables. In addition, two single diagnostic rules for diabetic and non-diabetic individuals were presented with accuracy of 70.83% and 81.48%, respectively. The number of pregnancies, body mass index, diastolic blood pressure, diabetes pedigree function, plasma glucose concentration and Triceps skin fold thickness were the most effective factors in having or not having diabetes in the extracted rules. Conclusion: The proposed model is quite suitable in producing an accurate and highly interpretable ruleset as well as individual diagnostic rules in medical applications. Moreover, because of its self-organizing ability, it is a general model and can be used in other binary classification applications.