Abstract: This paper discusses the performance of proposed learning method of Hybrid Back Propagation Neuro fuzzy Method (BPN) and Runge-Kutta Learning Method(RKLM). The proposed learning method is evaluated in the application of cancer classification. First, a classifier is trained with a part of samples in the cancer data set. Then one uses the trained classifier to predict the samples in the rest of the dataset to evaluate the effectiveness of the classifier. The analysis of the cancer classification using Hybrid Adaptive Neuro Fuzzy Inference System (ANFIS) is explained in this paper.