Share
Blog
Cite
Print
Email
BookmarkScienceDaily (June 28, 2007) — Oregon Health & Science University Cancer Institute researchers have developed a Web-based software program that can help head and neck cancer patients better predict their survivability.
See also:
"This new tool can help us make personalized predictions of conditional survival for an individual patient depending on his or her specific situation," said Sam Wang, M.D., Ph.D., principal investigator, Holman Pathway Resident in the Department of Radiation Medicine, OHSU School of Medicine.
Conditional survival is a statistical system that takes into account the age when the patient was diagnosed with cancer and the time elapsed since diagnosis. The new Web-browser software tool, called the regression model, can calculate a patient's conditional survival based on the patient's age, gender, race and tumor site, stage and aggressiveness.
In a previous study researchers, including Wang, demonstrated the concept of conditional survival for head and neck cancer. They showed the longer patients survive after diagnosis and treatment, their better their prognosis.
"This is the first time we have the ability to make a customized prediction of conditional survival probability for an individual head and neck cancer survivor, based on his or her specific characteristics," said Wang.
The long-term goal is to build similar software tools for other cancers, Wang explained,so that physicians will be able to give cancer patients more individualized prognosis and treatment recommendations.
"Now that cancer researchers are beginning to collect more specific information about patients' tumors, such as tumor markers and genetic information, there is increasing interest in the development of these types of tools for making more specific predictions of a patient's prognosis," Wang said.
The study was recently presented at the annual American Society of Clinical Oncologists.
Other researchers contributing to this study include: Clifton David Fuller, M.D., resident in the Department of Radiation Oncology and a trainee in Human Imaging/Radiobiology, Division of Radiological Sciences, University of Texas Health Science Center at San Antonio; Dean Sittig, Ph.D., director, Applied Research in Medical Informatics Northwest Permanente; John Holland, M.D., associate professor of radiation medicine, OHSU School of Medicine, a member of the OHSU Cancer Institute; and Charles Thomas Jr., M.D., chairman, Department of Radiation Medicine, OHSU School of Medicine and a member of the OHSU Cancer Institute.
The research was funded by a National Institutes of Health's National Library of Medicine post-doctoral fellowship in biomedical informatics.
