PMRA and Shapley-Based Machine Learning for Predicting Lymph Node Metastasis in Central Subregions of Clinically Node-Negative Papillary Thyroid Microcarcinoma: a Prospective Multicenter Validation and Development of a Web Calculator

PMRA and Shapley-Based Machine Learning for Predicting Lymph Node Metastasis in Central Subregions of Clinically Node-Negative Papillary Thyroid Microcarcinoma: a Prospective Multicenter Validation and Development of a Web Calculator

Background:Management of clinically node-negative(cN0) papillary thyroid microcarcinoma (PTMC) is complicated by high occult lymph node metastasis (LNM) rates. We aimed to develop and validate a prediction model for central LNM using machine learning (ML) and traditional nomograms through Probability-based Ranking Model Approach (PMRA).

Methods: We conducted a prospective multicenter study involving 4,882 patients across 3 hospitals (2016-2023). After applying inclusion criteria, 1,953 patients from the primary center were allocated to model train and test (7:3 ratio). External validation included prospective cohorts of 286 and 176 patients from two independent centers.13 ML algorithms and traditional nomogram models were systematically evaluated using PMRA.We compared models using preoperative features alone versus those incorporating both preoperative and intraoperative frozen section pathology data. Feature selection utilized six methods, with L1-based selection proving optimal for most predictions.Model interpretability was enhanced through SHapley Additive exPlanations (SHAP) visualization.

Inclusion Criteria:

• First-time thyroid cancer surgery patients
• cN0-PTMC patients diagnosed through fine-needle aspiration and imaging.

Exclusion Criteria:

• Secondary surgery
• Other pathological types of thyroid cancer
• Incomplete clinical data
• Distant metastasis or history of cervical radiation exposure.