A nomogram based on multimodal ultrasound and clinical features for the prediction of central lymph node metastasis in unifocal papillary thyroid carcinoma.

Abstract

To build a predictive model for central lymph node metastasis (CLNM) in unifocal papillary thyroid carcinoma (UPTC) using a combination of clinical features and multimodal ultrasound (MUS). This retrospective study, included 390 UPTC patients who underwent MUS between January 2017 and October 2022 and were divided into a training cohort (n = 300) and a validation cohort (n = 90) based on a cut-off date of June 2022. Independent indicators for constructing the predictive nomogram models were identified using multivariate regression analysis. The diagnostic yield of the 3 predictive models was also assessed using the area under the receiver operating characteristic curve (AUC). Both clinical factors (age, diameter) and MUS findings (microcalcification, virtual touch imaging score, maximal value of virtual touch tissue imaging and quantification) were significantly associated with the presence of CLNM in the training cohort (all P < .05). A predictive model (MUS + Clin), incorporating both clinical and MUS characteristics, demonstrated favourable diagnostic accuracy in both the training cohort (AUC = 0.80) and the validation cohort (AUC = 0.77). The MUS + Clin model exhibited superior predictive performance in terms of AUCs over the other models (training cohort 0.80 vs 0.72, validation cohort 0.77 vs 0.65, P < .01). In the validation cohort, the MUS + Clin model exhibited higher sensitivity compared to the CLNM model for ultrasound diagnosis (81.2% vs 21.6%, P < .001), while maintaining comparable specificity to the Clin model alone (62.3% vs 47.2%, P = .06). The MUS + Clin model demonstrated good calibration and clinical utility across both cohorts. Our nomogram combining non-invasive features, including MUS and clinical characteristics, could be a reliable preoperative tool to predict CLNM treatment of UPTC. Our study established a nomogram based on MUS and clinical features for predicting CLNM in UPTC, facilitating informed preoperative clinical management and diagnosis.