Risk factors and prognostic Nomogram for distant metastasis in patients with PTMC using classical statistics

Abstract There are some controversies about the choice of treatment for papillary thyroid microcarcinoma (PTMC), and the prediction model for distant metastasis(DM) of PTMC is urgently needed to guide the formulation of treatment plan. Therefore, we study retrospectively analyzed the Surveillance, Epidemiology, and End Results (SEER) database using classical statistics and machine learning to explore the risk factors and construct a novel DM prediction nomogram for DM in patients with PTMC(PTMC-DM).Data of patients with PTMC, covering 2004 to 2015, were gathered from the SEER database. Cox proportional hazards regression, Kaplan Meier methods and log-rank tests were conducted to identify the independent prognostic factors for predicting DM. These significant prognostic factors were used for the development of an DM prediction nomogram.Totally 27,933 PTMC samples gathered from the SEER database,72 patients (0.26%) had PTMC-DM at the time of diagnosis and 107 (0.38%) died from thyroid disease,were divided into training cohort and validation cohort (score construction and internal validation) at random. Multivariate Cox regression analysis showed that T stage, N stage, gender, and age were independent risk factors for DM in PTMC patients. The prognostic nomogram we constructed was also for DM. Additionally, calibration curves and decision curve analysis (DCA) curves revealed that the nomogram has excellent clinical utility.The prognosis characteristics of PTMC-DM was systematically reviewed. The nomogram we constructed can provide survival predictions to assist clinicians in making individualized decisions for appropriate treatment.