Fuzzy classification rules are more interpretable and cope better with pervasive uncertainty and vagueness with respect to crisp rules. Because of this fact, fuzzy classification rules are extensively used in classification and decision support systems for disease diagnosis. The proposed Rough Set Theory (RST)-BatMiner integrates the Rough Set Theory for feature selection and bat algorithm for fuzzy rule extraction. The proposed RST-BatMiner is experimentally tested on the Pima Indians Diabetes dataset and results are compared with other bio-inspired-based fuzzy rule miners using accuracy, sensitivity, specificity, number of rules, mean antecedent rule length and mean ruleset size. The rule learning process in RST-BatMiner is done separately for each class. The rules mined by RST-BatMiner are used to classify new instances in the test dataset. To validate robustness of the proposed fuzzy rule miner, it is further compared with several other bio-inspired approaches, which were used for mining of fuzzy classification rules.