Objective:

To develop a prediction model for central cervical lymph node metastasis (CLNM) in papillary carcinoma of the thyroid (PTC) by combining the patients’ basic clinical information

laboratory indexes

and ultrasound features. This model assists clinical preoperative evaluation and selects personalized treatment plans for patients.

Methods:

A total of 912 patients who underwent surgery for PTC were enrolled in the study. The enrolled patients were randomly divided into a training dataset (

n

=727) and a validation dataset (

n

=185). Univariate and multivariate analysis were performed to examine risk factors associated with CLNM. A nomogram comprising the prognostic model to predict the CLNM was established

and validation was performed in the validation cohort. Finally

clinical decision curve was used to evaluate its clinical application.

Results:

We developed a prediction model that included gender

age

total tumor diameter (TTD)

thyroid stimulating hormone (TSH)

calcification

and the thyroid lesion in contact with the thyroid capsule and Hashimoto’s thyroiditis. The nomogram showed area under curve (AUC) of 0.746 and 0.826 in the training cohort and validation cohort. Therefore

the model had higher sensitivity than preoperative ultrasound.

Conclusion:

The nomogram prediction model developed by logistic regression showed a good performance in predicting CLNM in PTC patients

and addressed the shortcomings of ultrasound diagnosis.