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.

A retrospective analysis was conducted on 4,882 cases from the First Affiliated Hospital of Chongqing Medical University (Hospital A) between 2016 and 2020, collecting clinical, ultrasound, and intraoperative frozen pathology data. After applying inclusion and exclusion criteria, 1,953 patients were selected for model development and internal validation (split in a 7:3 ratio). For prospective external validation, patients from two additional centers were included: 286 cases from Women and Children's Hospital of Chongqing Medical University (Hospital B) and 176 cases from The People's Hospital of Yubei District of Chongqing (Hospital C), designated as external validation sets 1 and 2, respectively.

The main reasons are as follows: IPD contains personal sensitive information, and sharing it may infringe on privacy and violate data protection regulations (such as GDPR). Sharing IPD may pose risks of data leakage or misuse, especially when it is not adequately anonymized. The use of data is subject to legal or contractual constraints and cannot be shared without permission. IPD may involve intellectual property rights or business secrets, and sharing it may affect the rights of data owners. Sharing IPD may violate the informed consent of research participants and trigger ethical disputes. The lack of background information may lead to incorrect interpretation or misuse of the data. The process of data preparation, anonymization, and sharing is time-consuming and labor-intensive, adding additional burdens. Therefore, IPD sharing should be done with caution and usually requires strict review and protection by agreement.