RESUMO
OBJECTIVE: To develop and validate a risk stratification system for the prediction of malignancy in partially cystic thyroid nodules (PCTNs). METHODS: We retrospectively reviewed the sonography data of patients with PCTNs from 2 medical centers-Hangzhou Traditional Chinese Medicine Hospital and Hangzhou First People's Hospital-from January 2020 to December 2021. The independent risk factors for malignant PCTNs were evaluated using the univariate and multivariate logistic regression analyses. The nomogram prediction efficiency was assessed using the area under the curve and calibration curves. The decision curve analysis was used to determine the clinical value of the predictive model. RESULTS: A total of 285 patients were enrolled in this retrospective study, and of 301 PCTNs, 242 were benign and 59 were malignant. Younger age, hypoechoic, irregular margin, and microcalcifications were found to be the independent risk factors for malignant PCTNs. The area under the curve, sensitivity, and specificity were 0.860, 77.1%, and 84.7% in the training data set and 0.897, 91.7%, and 87.0% in the external validation data set, respectively. The total point of nomogram was >161, which showed the best to predict malignancy in PCTNs. CONCLUSION: Our findings demonstrated that the risk stratification system for the assessment of PCTNs showed good prediction capacities.