Individualized estimation of conditional survival for patients with head and neck cancer.

Abstract

Survival for cancer patients is usually only reported as survival from time of diagnosis. For patients who survive 1 or more years after diagnosis, however, survival probability changes over time and is more accurately depicted by conditional survival. The specific aim of this project was to build a survival regression model and Web-based tool to make individualized estimates of conditional survival for patients with head and neck cancer based on tumor and patient characteristics. Using data from the Surveillance, Epidemiology, and End Results (SEER) database, a prediction modeling tool was built that can estimate prognosis for patients with head and neck cancer who have already survived a period of time after diagnosis. Having more accurate prognostic information may empower both patients and clinicians to make more appropriate decisions regarding follow-up, surveillance testing, and future treatment.