OBJECTIVE

This work aimed to construct and validate a model for predicting distant metastasis (DM) in thyroid carcinoma (TC) patients aged≥50.

PATIENTS AND METHODS

The research data were collected from the Surveillance, Epidemiology, and End Results (SEER) program databases via SEER*Stat software (https://seer.cancer.gov/). Logistics regression was used to screen the independent risk factors for TC patients. The nomogram was constructed and validated based on the logistics regression results for predicting DM occurrence in TC patients. Moreover, the characteristic curves (ROC) were used to assess the predictive performance. The decision analysis curve (DCA) and the calibration curve were used to test this nomogram's accuracy and discrimination. Additionally, we analyzed survival and risk scores in TC patients with metastasis using the Kaplan-Meier (KM) method.

RESULTS

A total of 11,166 TC patients were divided into a training set and a validation set. The results showed that topography (T), lymph node metastasis (N), and (grade) G were crucial risk factors for predicting DM. ROC analysis showed that the model had a good discriminative ability both in the training and validation set. The DCA curve showed greater net benefits across a range of DM risks for the nomogram in the training and validation set. Survival analyses showed that the metastasis cases with low-risk scores have shown a poorer prognosis in this study, both in the training and validation set.

CONCLUSIONS

The nomogram model had excellent predictive performance and net benefit for predicting DM of TC patients aged ≥50. The model can help doctors develop treatment plans for their patients.