Abstract:

Objective To develop a nomogram model based on clinical characteristics， intratumoral ultrasound features， and peritumoral ultrasound features for preoperative prediction of the risk of central lymph node metastasis （CLNM） in papillary thyroid microcarcinoma （PTMC）， and to evaluate its predictive performance and clinical applicability. Methods A total of 534 papillary thyroid microcarcinoma （PTMC） cases that underwent surgical treatment at the Second Affiliated Hospital of Guangzhou University of Chinese Medicine from February 2022 to April 2023 were retrospectively included. The cases were randomly allocated in a 7：3 ratio to a training cohort （n = 373） and a validation cohort （n = 161） using computer-generated random numbers. The participants were categorized into central lymph node metastasis （CLNM）-positive and CLNM-negative groups according to postoperative pathological findings. Clinical data and ultrasound imaging features were gathered. Independent risk factors for CLNM were determined using multivariable logistic regression analysis， and a predictive nomogram was developed based on these variables. The performance of the model was evaluated in terms of discrimination， calibration， and clinical utility using receiver operating characteristic （ROC） curves， area under the curve （AUC）， calibration plots， and decision curve analysis （DCA）. Results Multivariate analysis demonstrated that male sex， age less than 46.5 years， tumor heterogeneity， tumor contact with the thyroid capsule equal to or greater than 50%， and peritumoral hyperechoic changes were independent predictors of central lymph node metastasis （CLNM） （P < 0.05）. The nomogram model attained an area under the curve （AUC） of 0.857 （95%CI： 0.820 - 0.894） in the training cohort， with a sensitivity of 79.0% and a specificity of 80.0%. In the validation cohort， the AUC was 0.840 （95%CI： 0.778 - 0.902）， with a sensitivity of 94.1% and a specificity of 66.7%. Calibration plots showed good agreement between predicted and observed probabilities， and decision curve analysis （DCA） indicated a favorable net clinical benefit across a range of threshold probabilities. Conclusions The proposed nomogram， which integrates gender， age， and key ultrasonographic features， can effectively predict the risk of central lymph node metastasis （CLNM） in patients with papillary thyroid microcarcinoma （PTMC） pre-operatively. It demonstrates strong discriminative ability and calibration. This model may serve as a valuable tool for guiding individualized surgical decision-making.

Key words: ultrasound features, papillary thyroid microcarcinoma, central lymph node metastasis