Personalized prognosis: construction and validation of a survival prediction model for older postoperative differentiated thyroid cancer patients

The prognosis of older patients with postoperative differentiated thyroid cancer (DTC) is influenced by multiple factors. This study aimed to develop a nomogram to predict overall survival (OS) in older DTC patients. Data for 11,283 DTC patients aged 60 or older, diagnosed between 2000 and 2020, were extracted from the SEER database. Patients were randomly split into training and validation cohorts. Clinical variables associated with OS were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression with cross-validation. Model performance was assessed with the concordance index (C-index), calibration curves, and time-dependent area under the receiver operating characteristic curve (AUC). The nomogram’s clinical value was compared to the TNM staging system using decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI). K-fold cross-validation was applied to validate model robustness, and Kaplan–Meier analysis compared survival across risk groups. Ten variables were used to construct the nomogram. The nomogram achieved a C-index of 0.763 in the training and 0.739 in the validation cohorts, with AUCs over 0.75. Calibration showed good prediction alignment. NRI and IDI values demonstrated the nomogram’s superiority over TNM staging (P < 0.05). DCA suggested strong clinical applicability. This nomogram provides a robust tool for assessing OS in older postoperative DTC patients. Further studies should refine models with updated prognostic factors.