Two New Methods for Predicting Outcome in Cancer Patients

12:00 noon, Jan 22, Tuesday, 2008, by Dechang Chen, ST2, 430A

Abstract

The TNM (Tumor, Lymph Node, Metastasis) is a widely used staging system for predicting the outcome of cancer patients. However, the TNM is not accurate in prediction, partially due to the fact that TNM uses only three variables (tumor, lymph node, and metastasis) to group patients, leading to deficient staging within and between stages. Based on the availability of large cancer patient datasets, there is need to expand the TNM. In this talk, we present two new approaches to accomplish this task of expansion, one based on the idea of group testing and the other on the concept of clustering. Our approaches admit multiple factors. One major advantage is that patients within each generated group are homogeneous in terms of survival, so that a more accurate prediction of outcome of patients can be made. A demonstration of use of the proposed methods is given for lung and breast cancer patients.

Short Bio

Dr. Dechang Chen obtained his B.S. degree in mathematics from Southeast University, China, M.S. degree in mathematics from Peking University, China, M.S. degree in statistics and Ph.D. in mathematics from the State University of New York at Buffalo. He currently is an associate professor of the Department of Preventive Medicine and Biometrics at Uniformed Services University of the Health Science, Bethesda, Maryland. Dr. Chen’s research interests include bioinformatics, computational medicine, statistical learning, and data analysis in wireless networks. He was the organizer of DIMACS Workshop on Machine Learning Techniques in Bioinformatics, sponsored by NSF, in 2006 and the organizer of DIMACS Workshop on Computational Methods for Predicting Outcome in Cancer, sponsored by NSF, in 2007. Currently, his research is supported by three NSF regular grants. Dr. Chen has had about 80 publications.