An Interpretable Machine-Learning Model for Predicting Occult Central Lymph Node Metastasis in Papillary Thyroid Cancer

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Random forest model AUC 0.906 (training) and 0.733 (test set)

• Primary Outcome: Occult lymph node metastasis prediction in cN0 PTC patients

• Nnt Or Sensitivity: Brier scores 0.135 (training) and 0.212 (test); AUC 0.719 for tumors ≤1cm

• Confidence Interval: Not specified in abstract

Clinical Application

High feasibility with web-based calculator; requires molecular testing (BRAF, RET fusion) and detailed ultrasonography Relevant to Australian thyroid cancer management; molecular testing available through public pathology services; aligns with Cancer Council Australia thyroid cancer guidelines for risk stratification Clinically node-negative papillary thyroid cancer patients considering surgery, thermal ablation, or active surveillance

Abstract

CONTEXT: Accurate preoperative prediction of occult lymph node metastasis (OLNM) in clinically lymph node negative (cN0) papillary thyroid carcinoma (PTC) is critical for optimizing therapeutic strategy, particularly for thermal ablation and active surveillance. OBJECTIVE: The aim of this study was to develop an interpretable machine-learning (ML) model to predict the risk of OLNM in cN0 PTC patients. METHODS: This retrospective study analyzed data of 961 cN0 PTC patients (August 2018-August 2023). Multivariable logistic regression identified independent risk factors for OLNM in cN0 PTC. The cohort was randomly divided into the training and test sets, and a subset of patients with tumors sized 1 cm or less was further extracted from the test set for internal validation. Eight ML models incorporating clinical, ultrasonographic, and molecular features were developed and evaluated. Shapley Additive exPlanations (SHAP) enhanced interpretability. RESULTS: RET fusion positivity and BRAF mutation positivity were identified as independent molecular risk factors for OLNM in cN0 PTC, alongside 6 clinical and ultrasonographic variables. Nine predictors were incorporated into the predictive model. The random forest (RF) model achieved optimal performance with an area under the curve (AUC) of 0.906 in the training set and 0.733 in the test set, along with the lowest Brier scores of 0.135 and 0.212, respectively. Analysis of tumors sized 1 cm or less internally validated the model's robustness with an AUC of 0.719. SHAP analysis identified size, age, and clustered punctate echogenic foci as the top predictors. CONCLUSION: This is the first study to identify RET fusion positivity as an independent OLNM risk factor in cN0 PTC. The developed RF model demonstrates moderate predictive performance for OLNM risk and provides a framework for integrating clinical, sonographic, and molecular data, and is deployed as a web calculator (https://predictingoccultlymphnodemetastasis.shinyapps.io/web3/).

References

1. 1.Wang, Z., Yang, S., Li, Y., Tian, J., Li, Y., Jiang, K., Liu, R., Zhang, Y., Zhu, X., Hu, A., & Li, Q. (2026). An interpretable machine-learning model for predicting occult central lymph node metastasis in papillary thyroid cancer. The Journal of Clinical Endocrinology and Metabolism. https://doi.org/10.1210/clinem/dgaf636