A Clustering-Based Approach to Predict Outcome in Cancer Patients

Xiuzhen Cheng, Ph.D., Assistant Professor, Department of Computer Science
Donald Henson, M.D., Project Manager, GW Cancer Institute

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 of deficient staging within and between stages. Based on the availability of large cancer patient datasets, there is a need to expand the TNM. In this talk, we present a general clustering-based approach to accomplish this task of expansion. Our approach admits multiple factors. One major advantage of the approach 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 method is given for breast cancer patients.

[Talk Slides]

Biographies:

Donald E. Henson, M.D. is Adjunct Professor of Pathology and Adjunct Professor of Epidemiology and Biostatistics at The George Washington University School of Medicine. He is also Co-Director of the Office of Cancer Prevention and Control at The George Washington University Cancer Institute. Board Certified in Pathology, Dr. Henson trained at Rush Presbyterian St Luke's Hospital in Chicago. After a year of post doctoral training, Dr. Henson joined the National Institutes of Health and eventually the Laboratory of Pathology of the National Cancer Institute. In addition to pathology, Dr. Henson has served in the Division of Cancer Prevention as Program Director in the Early Cancer Detection program. Research interests have included the analysis of prognostic factors, diagnostic encoding, and the morphology of precancerous lesions. He has served as a consultant to the World Health Organization and to the Pan American Health Organization. He has also served as Chair of the American Joint Committee on Cancer and Chair of the Cancer Committee of the College of American Pathologists. Dr. Henson has published more than 185 peer reviewed manuscripts and 15 books and manuals including a book on the Pathology of Incipient Neoplasia. Currently, Dr. Henson is Co-Chair of the Washington DC Cancer Consortium, and Chair of the Quality Management Subcommittee at The George Washington University Hospital.

Dr. Cheng's research interests are centered on algorithm design and analysis targeting problems originated from wireless networks and computational medicine. She has been working on a clustering-based prognostic system to predict the outcome of cancer patients. Currently her research is mainly focused on the development and application of machine learning techniques to evaluate and identify risk factors for cancer and conduct clinical outcome and survival prediction. Dr. Cheng was a program director of the National Science Foundation for six months in 2006. She received the NSF CAREER Award in 2004.