Abstract
Prophylactic dissection of the paratracheal lymph nodes in clinical lymph node-negative (cN0) papillary thyroid carcinoma (PTC) remains controversial, as it is difficult to accurately assess the status of the paratracheal lymph nodes preoperatively. This study aimed to construct and validate an interpretable predictive model for paratracheal lymph node metastasis (PLNM) in cN0 PTC using machine learning (ML) methods. We retrospectively selected 3,212 PTC patients treated at the First Affiliated Hospital of Chongqing Medical University from 2016 to 2020. They were randomly divided into the training and test datasets with a 7:3 ratio. The 533 PTC patients treated at the Guangyuan Central Hospital from 2019 to 2022 were used as an external test set. Nine ML models, including XGBoost, were developed. The predictive performance was evaluated using ROC curves, decision curve analysis (DCA), calibration curves, and precision-recall curves. SHapley Additive exPlanations (SHAP) were used to interpret the top 10 predictive features, and a web-based calculator was created. The XGBoost model achieved AUC values of 0.935, 0.857, and 0.775 in the training, validation, and test sets, respectively, significantly outperforming the traditional nomogram model with AUCs of 0.85, 0.844, and 0.769, respectively. SHAP-based visualizations identified the top ten predictive features: prelaryngeal and pretracheal LNMR, tumor size, pretracheal LNMR, prelaryngeal and pretracheal LNM, age, tumor border, pretracheal LNM, pretracheal NLNM, side of position, calcification. These features were used to develop a web-based calculator. ML is a reliable tool for predicting PLNM in cN0 PTC patients. The SHAP method provides valuable insights into the XGBoost model, and the resultant web-based calculator is a clinically useful tool to assist in the surgical planning for paratracheal lymph node dissection.