Abstract
AIM: Accurate preoperative prediction of cervical lymph node metastasis (LNM) in patients with mPTMC provides a basis for surgical decision making and the extent of tumor resection. This study aimed to develop and validate an ultrasound radiomics nomogram for the preoperative assessment of LN status. METHODS: A total of 450 patients pathologically diagnosed with mPTMC were enrolled, including 348 patients in the modeling group and 102 patients in the validation group. Univariate and multivariate logistic regression analyses were performed on the basic information, ultrasound characteristics, and American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) scores of the patients in the modeling group to identify independent risk factors for LNM in mPTMC and to construct a logistic regression equation and nomogram to predict the risk of LNM. The validation group data were used to evaluate the predictive performance of the nomogram. RESULTS: Male sex, age <40 years, a single lesion with a maximum diameter >0.5 cm, capsular invasion, a maximum ACR score >9 points, and a total ACR score >19 points were independent risk factors for the development of cervical LNM in mPTMC. Both the area under the curve (AUC) and concordance index (C-index) of the prediction model constructed from the above six factors were 0.838. The calibration curve of the nomogram was close to the ideal diagonal line. Furthermore, decision curve analysis (DCA) demonstrated a significantly greater net benefit of the model. The external validation demonstrated the reliability of the prediction nomogram. CONCLUSIONS: The presented radiomics nomogram, which is based on ACR TI-RADS scores, shows favorable predictive value for the preoperative assessment of LNs in patients with mPTMC. These findings may provide a basis for surgical decision making and the extent of tumor resection.