# Nomogram prediction for central lymph node metastasis in papillary thyroid microcarcinoma of the isthmus based on clinical and ultrasound features

## TL;DR

This study creates a tool to predict lymph node metastasis in a specific type of thyroid cancer using patient and ultrasound data.

## Contribution

A novel nomogram is developed to predict central lymph node metastasis in isthmic papillary thyroid microcarcinoma.

## Key findings

- Four independent risk factors for CLNM were identified: age, tumor size, multifocality, and calcification.
- The nomogram achieved an AUC of 0.811 and a C-index of 0.783, showing strong predictive performance.
- Decision curve analysis confirmed the model's clinical utility and net benefits.

## Abstract

To better predict the central lymph node metastasis (CLNM) of patients with isthmic papillary thyroid microcarcinoma (IPTMC) before surgery, we developed a new predictive nomogram based on clinical and ultrasound features and validate its reliability.

Our study included 160 patients who were hospitalized from January 2016 to December 2024, underwent thyroidectomy with lymph node dissection, and were pathologically diagnosed with IPTMC. These patients were randomly divided into a training group of 112 cases and a validation group of 48 cases. Clinical and ultrasound characteristic data of the patients were collected. Univariate and multivariate logistic regression analyses were conducted on the training group to determine the independent risk factors for CLNM, and a nomogram was established based on these factors to predict the risk of CLNM in patients with IPTMC. The predictive performance of the nomogram was verified using the validation group.

Among the clinical and ultrasound features in the training cohort, we identified four independent risk factors for CLNM: age, tumor size, multifocality, and calcification. A predictive nomogram was developed based on the above four risk factors. The predictive nomogram showed excellent calibration in predicting CLNM, with an area under the curve (AUC) of 0.811 and a concordance index (C-index) of 0.783. The calibration curve of the nomogram was close to the ideal diagonal. In addition, decision curve analysis (DCA) proved that the model had significantly greater net benefits. The validation group verified the reliability of the prediction nomogram.

The nomogram model developed in this study can effectively predict the risk of CLNM in patients with IPTMC before surgery and provide a reference for selecting surgical procedures.