Preoperative Risk Research Tool
Peer review in progress
Clinically node-negative papillary thyroid carcinoma

Occult central lymph node metastasis risk assessment

Compare the selected stacking ensemble with XGBoost using the same nine preoperative predictors. The tool is designed for the preoperative decision point after cN0 status has been established.

Prediction access is currently locked.

The manuscript and model are undergoing peer review. Public use is planned only after formal publication and release of the validated model version.

Choose a model

Review each model’s retrospective discrimination before viewing the shared inputs.

Model

Stacking ensemble

Selected for its highest internal test AUC (0.913). Stacking combines 11 base learners with a regularized logistic meta-learner. Its multiple training and prediction stages make implementation and maintenance more complex than XGBoost.

Internal test

0.91395% CI 0.883–0.939

Temporal validation

0.89495% CI 0.862–0.920

Geographical validation

0.89695% CI 0.864–0.924
AUC comparison between stacking and XGBoost
ModelInternal testTemporalGeographicalArchitecture and complexity
Stacking0.9130.8940.89611 base learners + logistic meta-learner; more fitting stages and model components
XGBoost0.9110.9010.894One boosted-tree algorithm; fewer model components and a simpler deployment workflow

Performance values are AUCs. The geographical AUC difference was 0.002 (stacking minus XGBoost; P=0.703). Complexity refers to model architecture and implementation. Prediction remains locked during peer review.

Model inputs — Stacking ensemble

Input definitions are shown for transparency. Data entry and prediction are disabled during peer review.

Research preview only