Development and validation of the BRAFV600E prediction model from clinical and ultrasound features in papillary thyroid carcinoma: a large cohort study.

BACKGROUND: The preoperative prediction of BRAFV600E mutation could help in devising appropriate strategies for patients with papillary thyroid carcinoma (PTC). This study aimed to develop and validate a nomogram based on clinical and ultrasound features to predict BRAFV600E mutation in PTC patients. METHODS: Between January 2018 and May 2023, a total of 4601 patients with PTC from one center were enrolled in this study. These patients were randomly divided into a training set (n = 3220) and an internal validation set (n = 1381) at a 7:3 ratio. Patients from another center were assigned to an external validation set (n = 737). Univariate and multivariate analyses were performed to identify independent predictors and establish the nomogram model. The area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA) were used to evaluate the nomogram. RESULTS: Four variables (Hashimoto's thyroiditis, echogenicity, shape, and echogenic foci) were selected to construct the nomogram for predicting the BRAFV600E mutation in patients with PTC. The AUCs for the training set, internal validation set, and external validation set were 0.812 (95% CI: 0.798-0.826), 0.797 (95% CI: 0.774-0.817), and 0.714 (95% CI: 0.680-0.746), respectively. Calibration curves for the nomogram showed good consistency between the predicted and actual probabilities. DCA indicated significant net benefits, supporting its clinical applicability. CONCLUSIONS: The nomogram, based on Hashimoto's thyroiditis, echogenicity, shape, and echogenic foci, demonstrates good performance in predicting the BRAFV600E mutation in PTC. The model may serve as a useful tool for individualized risk assessment in PTC patients.