Published on
Survival prediction is important both to clinicians and patients; ensuring the best course of treatment is selected to manage the thyroid cancer. In 2018, there was an estimated half a million new thyroid cancer diagnoses and 41,071 deaths. Unlike other tumors whose mortality has decreased over the last two decades, thyroid cancer mortality rates have increased. Existing risk stratification systems fail to account for microcarcinomas, which accounted for 28.6 percent of thyroid cancer diagnoses and 32.5 percent of papillary thyroid cancer diagnoses. They are also based upon a varying combination of 10 variables and have not considered newly identified variables available in current research. Additionally, current systems are noted to be complicated for daily use making their practicality questionable. To overcome these problems, this research seeks to identify new prognostic factors that have been published in the literature. Using the prognostic factors identified, along with previously utilized risk variables, a new analysis performed. A tree-based survival model utilizing random forest will yield a powerful risk stratification tool that can be used by clinicians and the patients they treat.
For Zoom information, please contact Robert Sanders (sandersrl@umsystem.edu).