Objective To construct and compare risk prediction models for skip metastasis,defined as lateral lymph node metastasis(N1b) without central compartment involvement,in N1b papillary thyroid carcinoma (PTC) patients by using multiple machine learning algorithms, and to provide clinical guidance through model interpretation and visualization. MethodsA retrospective analysis of 573 N1b PTC patients who were admitted between November 2011 and August 2024 in Zhongshan Hospital Affiliated to Xiamen University was conducted. Patients were randomly divided into training (70%, n=402) and testing (30%, n=171) sets by using R package caret. The training set is only used to build the model, and the test set is only used for model validation.Train Five machine learning models including logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost) by using 10-fold cross-validation on the training set to determine hyperparameters, then refit the models and validate them on the test set.Model performance was evaluated via the area under the receiver operating characteristic curve (AUC). Shapley additive explanations (SHAP) was employed for interpretability, and the optimal model was deployed as a web-based calculator using R Shiny. ResultsThe overall skip metastasis rate was 12.7% (73/573) in N1b PTC patients, with 12.9% (52/402) in the training set and 12.3% (21/171) in the testing set (P>0.05 for baseline comparisons). 11 predictors (age, age≥55, sex, maximum tumor diameter, tumor size≤1cm, upper pole involvement, multifocality, unilateral lobe involvement, extrathyroidal extension, capsular invasion, and Hashimoto’s thyroiditis) were used to develop the model. Training set: XGBoost, ［0.824±0.070, 95%CI (0.780, 0.868)］; LR, 0.802±0.065 ［95%CI (0.762, 0.842)］; DT, 0.773±0.141 ［95%CI (0.685, 0.861)］; RF, 0.767±0.068 ［95%CI (0.725, 0.809)］; SVM, 0.647±0.103 ［95%CI (0.583, 0.711)］. Testing set: XGBoost ［0.777, 95%CI (0.667, 0.887); LR, 0.769 ［95%CI (0.655, 0.883)］; DT, 0.737 ［95%CI (0.615, 0.858)］; RF, 0.757 ［95%CI (0.649, 0.865)］; SVM, 0.674 ［95%CI (0.522, 0.826)］. XGBoost was the optimum model which achieved the highest AUC in both training and testing sets. SHAP analysis identified the top six predictors: upper pole involvement (mean absolute SHAP: 0.249), maximum tumor diameter (0.119), extrathyroidal extension (0.078), age (0.065), unilateral lobe involvement (0.018), and capsular invasion (0.013). The XGBoost-based web calculator is accessible. ConclusionsThe XGBoost model demonstrated superior predictive performance among five machine learning algorithms. The developed web-based calculator offers clinical utility for assessing skip metastasis risk in N1b PTC patients.