Objective To construct and validate an interpretable machine learning model integrating contrast-enhanced venous phase CT radiomics and clinical features for preoperative prediction of central lymph node metastasis(CLNM)of papillary thyroid carcinoma(PTC).Methods A case-control study was conducted on 243 histologically confirmed PTC patients.Among them,196 patients from the First Affiliated Hospital of Army Medical University were randomly allocated into a training set(n=137)and an internal validation set(n=59)at a 7:3 ratio,while the left 47 patients from No.958 Hospital of PLA Army were assigned into an external validation set.All participants completed standardized preoperative contrast-enhanced neck CT scanning.Quantitative radiomic features were systematically extracted from venous phase CT images through an open-source big data AI platform.Six machine learning classifiers,eXtreme Gradient Boosting(XGBoost),Support Vector Machine(SVM),Random Forest(RF),Logistic Regression(LR),k-Nearest Neighbors(KNN),and Decision Tree(DT)were implemented to construct clinical-radiomics integration models.The predictive performance was quantitatively assessed through receiver operating characteristic(ROC)curve analysis,with area under the curve(AUC)values calculated for training,internal validation,and external validation sets.Model interpretability was achieved using Shapley additive explanations(SHAP)framework,with particular focus on elucidating feature contributions in the best-performing model.Results The XGBoost model had an AUC value of 0.936(95%CI:0.895～0.976),0.832(95%CI:0.724～0.941),and 0.772(95%CI:0.632～0.912)in training,internal and external validation sets,respectively.SHAP analysis revealed age as the most influential clinical predictor,with younger patients showing higher CLNM risk(OR=0.968,P=0.042).Conclusion Our machine learning-based clinic-radiomic prediction model demonstrates satisfactory performance in predicting CLNM of PTC,providing valuable references for clinical decision-making.

Objective To investigate the predictive value of a nomogram for central lymph node metastasis(CLNM)in patients with papillary thyroid microcarcinoma(PTMC)based on CT features combined with clinical factors.Methods A case-control study was conducted on 256 pathologically confirmed PTMC patients from 2 tertiary hospitals from January 2022 to November 2024.All participants underwent contrast-enhanced neck CT scanning within 2 weeks before surgery and received central lymph node dissection.The 201 patients from the First Affiliated Hospital of Army Medical University were randomized into a training set(n=140)and an internal validation set(n=61)in a 7∶3 ratio.The 55 patients from the Second Affiliated Hospital of Chongqing Medical University were all assigned into an external validation set.Their clinical data and CT features were collected.Univariate and multivariate logistic regression analyses were employed to identify independent predictive factors for CLNM,and then a nomogram model was constructed.Receiver operating characteristic(ROC)curve analysis(area under the curve,AUC),calibration curve,and decision curve analysis(DCA)were performed to evaluate the model performance,discrimination and clinical utility.Results Multivariate logistic regression analysis identified 4 independent CLNM predictors(P<0.05),that is,male(OR=5.991,95%CI:2.209～18.350),tumor size≥0.82 cm(OR=18.880,95%CI:1.803～229.500),capsular involvement(OR=9.805,95%CI:4.015～26.340),and CT-diagnosed lymph node positivity(OR=2.872;95%CI:1.176～7.232).The nomogram achieved an AUC value of 0.859(95%CI:0.796～0.922),0.786(95%CI:0.671～0.901),and 0.783(95%CI:0.648～0.917)in the training and internal and external validation sets,respectively.Calibration curves demonstrated high consistency between predicted and observed probabilities(Hosmer-Lemeshow P>0.05).DCA confirmed net clinical benefits for CLNM before surgical treatment with a threshold probability range of 0.18～0.80.Conclusion Based on sex,tumor size,capsular involvement,and CT-diagnosed lymph node metastasis,our nomogram model effectively predicts CLNM risk in PTMC patients.It can be used as a quantitative tool for personalized surgical planning and shows high clinical applicability.

Objective To evaluate the change of clinicopathological features and prognosis of papillary thyroid cancer over a 15-year period.Methods The clinicopathological features and outcomes of papillary thyroid cancer patients were analyzed in three groups according to the time of diagnosis:group Ⅰ (1997-2001),group Ⅱ (2002-2006),and group Ⅲ (2007-2011).Results As time advanced,the average age of papillary thyroid cancer patients increased,tumor stage,like size,extrathyroid invasion and lymph node metastasis decreased dramatically (P ＜ 0.01).The percentage of multifocality and bilaterality increased.The long-term follow up data (median follow up time was 6.6 years),indicated that the 15-year over all survival was 97.8％ and the 15-year disease-free survival was 90.2％.Tumor ≥3 cm,bilaterality,extrathyroid invasion,lymph node metastasis and AJCC stage were correlated with tumor recurrence.By multivariate COX-regression analysis only lymph node metastasis and bilaterality were independent risk factors.Conclusion The clinicopathological features of papillary thyroid cancer changed over 15 years,with the percentage of early-staged patients increased.Lymph node metastasis and bilaterality are two risk factors for tumor recurrence.