Personalized prediction of lymph node metastasis in papillary thyroid microcarcinoma: a nomogram and web calculator

Abstract

Abstract To analyze clinical and laboratory data of patients, identify indicators associated with lymph node metastasis (LNM) in papillary thyroid microcarcinoma (PTMC), and develop a nomogram and web-based calculator for predicting LNM risk. A retrospective analysis was performed on 754 patients who underwent PTMC resection between January 2018 and July 2023. Patients were randomly divided into a modeling set and a validation set at a 7:3 ratio. Independent predictive factors for LNM were identified using LASSO-logistic regression, and a nomogram was constructed. Model discrimination and calibration were assessed using ROC curves, calibration plots, the C-index, and the Hosmer–Lemeshow test. The modeling set included 528 cases (392 non-metastatic, 136 metastatic), and the validation set comprised 226 cases (175 non-metastatic, 51 metastatic). LASSO-logistic regression identified nodule diameter, gender, albumin, apolipoprotein B, and thyroglobulin as independent predictors of LNM. The predictive model achieved AUROC values of 0.758 in the modeling set and 0.696 in the validation set. Calibration plots, the C-index, and the Hosmer–Lemeshow test demonstrated good agreement between predicted and observed risks. Decision curve analysis (DCA) and clinical impact curves (CIC) indicated favorable clinical benefit and impact. The model was also implemented as a freely accessible web-based calculator (https://ley120.shinyapps.io/Lymph_Node_Metastasis_in_PTMC/). This study developed a nomogram and web-based calculator to predict LNM risk in PTMC. The model may assist clinicians in estimating LNM risk by entering relevant patient variables. This study was registered in the Chinese Clinical Trial Registry (ChiCTR2400080625).