Abstract: A hybrid algorithm of a particle swarm optimization and a fuzzy rule-based classification system is proposed in this study to diagnose breast cancer. Two orthogonal and triangular types of fuzzy sets are applied to represent the input variables. In additional, different input membership functions are considered to increase the classification accuracy. The performance of the proposed hybrid algorithm is studied using a classification accuracy measure on the Wisconsin breast cancer dataset. The results of the comparison using different training data sets show the higher performance of the proposed methodology.