Web tool predicts survival for cancer patients

Web tool predicts survival for cancer patients

Posted by Roland Piquepaille @ 8:35 am

Researchers at the Oregon Health & Science University Cancer Institute have developed a Web-based software program that can help some cancer patients to predict their survivability. ‘This modeling Web tool can help us make personalized predictions of conditional survival for an individual patient,’ said one of the researchers. For obvious reasons including privacy and security, this software tool is only available to physicians. Right now, the tool can only be used for patients affected with head or neck cancers. But the researchers want to build similar software tools for other cancers.

These modeling tools have been developed under the supervision of Samuel Wang who published a previous study on the same subject, “Analysis For Survival On Head and Neck Cancers.” (March 14, 2007)

Here are more details about this modeling tool. “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.

This research work has been presented at the annual meeting of the American Society of Clinical Oncology. It was also published in a special issue of the Journal of Clinical Oncology under the name “A regression model for predicting conditional survival for head and neck cancer patients: A SEER analysis” (Vol. 25, No. 18S, June 20 Supplement, 2007). Here is a link to the abstract of this study.

This is the introduction to this study. “Survival probability changes as patients survive longer periods of time after diagnosis, and estimates of prognosis at diagnosis are no longer valid. Conditional survival (CS) accounts for the changing hazard rate over time and is a more accurate estimate of survival probability for these cancer survivors. The specific aim of this project was to build a statistical model and web-based tool to predict conditional survival for an individual head & neck cancer patient based on tumor and patient characteristics.”

And this is a description of the methods which were used. “Using 27,825 patients diagnosed with head & neck cancer between 1988–97 from the Surveillance, Epidemiology, and End Results 17 (SEER) database, we built a multivariate Cox proportional hazards regression prediction model. Patient and tumor characteristics included as covariates were age, sex, race, tumor site, stage, and grade. The primary endpoint was conditional overall survival. The model was validated for discrimination using the concordance index and a calibration plot was constructed. Bootstrapping was used to correct for optimistic bias. We also built a web-browser software tool to allow a user to enter patient information into the model and calculate conditional survival probability.”

Apparently, the researchers obtained pretty good results with their regression model. Here are their conclusions. “Our regression model can accurately predict conditional survival for head & neck cancer patients based upon specific patient and tumor characteristics. This tool allows the calculation of more specific prognosis predictions for individual cancer patients who have already survived a period of time after diagnosis and treatment.”

Sources: Oregon Health & Science University Cancer Institute news release, June 27, 2007; and various websites