NCT06871956: PMRA

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

Completed Last updated 12 March 2025

What this trial tests

trial testing PMRA and Shapley-Based Machine Learning for Predicting Lymph Node Metastasis in Central Subregions of Clinically Node-Negative Papillary Thyroid Microcarcinoma in Papillary Thyroid Microcarcinoma in 4,882 participants. Completed in 31 December 2023.

Timeline

1 January 2016

Primary endpoint
31 December 2023

31 December 2023

Quick facts

Lead sponsor	First Affiliated Hospital of Chongqing Medical University
Status	Completed
Study type	OBSERVATIONAL
Enrollment	4,882
Start date	1 January 2016
Primary completion	31 December 2023
Estimated completion	31 December 2023
Sites	1 location across China

Drugs / interventions tested

• PMRA and Shapley-Based Machine Learning for Predicting Lymph Node Metastasis in Central Subregions of Clinically Node-Negative Papillary Thyroid Microcarcinoma

Conditions studied

• Papillary Thyroid Microcarcinoma — all drugs for Papillary Thyroid Microcarcinoma →

Sponsor

First Affiliated Hospital of Chongqing Medical University

Who can join

Eligibility, any sex, with Papillary Thyroid Microcarcinoma. Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

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.

Publications & conference data

No peer-reviewed publications indexed yet for this trial. Completed trials usually publish results within 12-18 months.