AUTHOR=He Liang , Xiang Jingzhe , Zhang Hao TITLE=Rethinking the prognosis model of differentiated thyroid carcinoma JOURNAL=Frontiers in Endocrinology VOLUME=Volume 15 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2024.1419125 DOI=10.3389/fendo.2024.1419125 ISSN=1664-2392 ABSTRACT=The prediction efficiency of long-term cancer-specific survival (CSS) to guide the treatment of differentiated thyroid cancer (DTC) patients is still unsatisfactory. We need to refine a system more accurately correlate with survival.Methods: This is a retrospective study using the Surveillance, Epidemiology and End Results (SEER) database, which included patients who underwent surgical treatment and diagnosed with DTC from 2004 to 2020. Patients were divided into training cohort (2004-2015) and validation cohort (2016-2020). Decision tree methodology was used to build the model in training cohort. The newly identified groups were verified in validation cohort.Results:52917 and 48896 patients with DTC were included in training cohort and validation cohort. Decision tree classification of DTC patients was consisted of five categorical variables which in order of importance were the following: M categories, age, extrathyroidal extension, tumor size and N categories. Then we identified 5 TNM groups with similar within-group CSS. More patients were classified as stage I, and the number of stage IV decreased significantly. The new system has a higher proportions of variance explained (PVE) (5.04%) and lower Akaike information criterion (AIC) (18331.906) than the 8 th TNM staging system (PVE for 4.11% and AIC for 18692.282). In validation cohort, the new system also showed better discrimination on survival.The new system for DTC appeared to be more accurate on distinguishing stages according to risk of mortality, which provided more accurate risk stratifications and potential treatment selections.