Published on Nov. 12, 2018

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 will be 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 not decreased, the have increased.  Existing risk stratification systems fail to account for microcarcinomas, which accounted for 28.6 percent of thyroid cancers and 32.5 percent of papillary thyroid cancer.  They are also based upon a varying combination of 10 variables and have not considered newly identified variables in current research.  Additionally, current systems are noted to be complicated for daily use making their practicality questionable.  To overcome this problem, a new analysis of prognostic risk factors will be performed.  A tree-based model will yield a powerful data analytics tool for clinicians and the patients they treat.