南京医科大学学报（自然科学版）2026，Vol.46Issue(1)：14-20,7.DOI:10.7655/NYDXBNSN250910
基于多模态数据的甲状腺髓样癌中央区淋巴结转移术前预测模型的构建与分析
Construction and analysis of a preoperative prediction model for central lymph node metastasis in medullary thyroid carcinoma based on multimodal data
摘要
Abstract
Objective:To develop and validate a multimodal data-based predictive model for central lymph node metastasis(CLNM)in patients with medullary thyroid carcinoma(MTC)and evaluate its clinical significance.Methods:We retrospectively analyzed clinical-pathological data,preoperative imaging features,and laboratory parameters of 104 MTC patients treated at the First Affiliated Hospital of Nanjing Medical University between January 2017 and May 2025.Potential predictors(P<0.1 in univariate analysis)were included in a multivariate logistic regression model with backward stepwise selection to identify independent risk factors for CLNM.A prediction model was constructed and a nomogram was drawn.The receiver operating characteristic(ROC)curve,calibration curve and decision curve analysis(DCA)were used to evaluate the discrimination,calibration,and clinical applicability of the model.Internal validation was performed via bootstrap resampling.Results:According to the presence or absence of CLNM in the pathological results,104 MTC patients were classified into CLNM-positive(n=55)and CLNM-negative(n=49)groups.Compared to the CLNM-negative group,CLNM-positive patients showed significant differences in sex(P=0.001),whether the ultrasound(US)tumor morphology was regular(P<0.001),whether US tumor margin was smooth(P<0.001),serum carcinoembryonic antigen(CEA)level(P=0.006),and serum calcitonin(CT)level(P<0.001).Multivariate analysis identified male gender(OR=6.50,95%CI:2.03-20.81;P=0.002),non-circumscribed US margins(OR=9.77,95%CI:3.12-30.59,P<0.001),and elevated serumCT(OR=1.25,95%CI:1.10-1.42,P<0.001)as independent risk factors for CLNM.The nomogram integrating these factors demonstrated excellent discrimination(AUC=0.873,95%CI:0.808-0.939),with good calibration and clinical utility on DCA.Bootstrap validation confirmed model stability(AUC=0.874,95%CI:0.865-0.879).Conclusion:A multimodal model incorporating sex,US tumor margin status,and serum CT levels effectively predicts CLNM risk in MTC patients,providing a valuable tool for clinical decision-making.关键词
甲状腺髓样癌/中央区淋巴结转移/多模态数据/预测模型Key words
medullary thyroid carcinoma/central lymph node metastasis/multimodal data/prediction model分类
医药卫生引用本文复制引用
ZHANG Xiang,LIU Wei,YANG Qianqian,ZHANG Yan..基于多模态数据的甲状腺髓样癌中央区淋巴结转移术前预测模型的构建与分析[J].南京医科大学学报（自然科学版）,2026,46(1):14-20,7.基金项目
江苏省医学重点学科(ZDXK202239) （ZDXK202239）
