Rule Based Classification System for Medical Data Mining Using Fuzzy Ant Colony Optimization

Pattern recognition systems have been extensively used in healthcare to mine patient data to discover a predictive model that makes reliable predictions. The objective of this paper is to utilize a hybridization of Ant Colony Optimization (ACO) and Fuzzy Logic to extract a set of fuzzy rules for classification of medical data. We will comment on some recent works and describe a new and efficient approach that leads us to significant results for medical classification problems, named Fc-AntMiner. Fc-AntMiner generates a set of fuzzy classification rules from labeled data by using an ACO-based learning algorithm. These rules are represented in linguistic forms that are easily interpreted and examined by users. The results reveal that Fc-AntMiner outperforms several famous methods in classification accuracy for medical classification.