An Expert System for Breast Cancer Diagnosis Using Fuzzy Classifier with Ant Colony Optimization

Medical diagnosis is a complex process in which the result of the diagnosis has to be more accurate. Medical expert systems can assist physicians to make fast, accurate and meaningful clinical decisions. This paper proposes a medical decision support system based on fuzzy logic and Ant Colony Optimization (ACO) for the breast cancer diagnosis using Wisconsin’s breast cancer dataset of UCI machine learning repository. A set of fuzzy rules are extracted from patient dataset using Fuzzy Logic and ACO. The ACO algorithm optimizes these extracted fuzzy rules and generates optimized set of rules. The fuzzy inference system uses these optimized rules to perform classification of the test data. Ten-fold cross validation procedure is used to evaluate the performance of the system in terms of the classification accuracy. The results show that the proposed model achieves better accuracy with other existing systems in the literature.