Abstract: In this study we show that the gene-expression profiles based on microarray analysis can be used to predict the genes which are responsible for death of the patient in early-stage B-cell Lymphoma. This study presents a new computational method for this prediction and use an informative subset of samples to identify genes whose expression is related to the problem under study. A reduction technique integrating global normalization, fuzzy membership generation, Pearson`s correlation method are used to identify genes which are related to non survival. The early identification of the genes causing B-cell Lymphoma that leads to death will benefit patients in the sense that the patients can be provided proper therapy to increase their life span. The validity of the results are established with the help of statistical methods.