ORIGINAL RESEARCH article
Front. Oncol.
Sec. Head and Neck Cancer
Volume 15 - 2025 | doi: 10.3389/fonc.2025.1565727
Development and Evaluation of a Clinical-Biochemical Nomogram for Differentiating Pleomorphic Adenoma and Warthin's Tumor in the Parotid Gland
Provisionally accepted
- First Affiliated Hospital, Guangxi Medical University, Nanning, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Objectives This study aims to construct and evaluate an integrated nomogram model that combines clinical characteristics and biochemical blood markers to enable accurate and cost-effective differentiation between PA and WT. Methods A retrospective analysis was carried out on patients diagnosed with PA and WT at the First Affiliated Hospital of Guangxi Medical University between 2013 and 2022. The participants were randomly allocated to the training set or validation set in a 3:1 ratio. Independent predictors were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression. Based on these predictor variables, a nomogram model was developed. The study systematically evaluated the diagnostic performance, calibration effects, and clinical utility of the model through the application of receiver operating characteristic curves (ROC), calibration curves, decision curve analysis (DCA), and clinical impact curves (CIC). Results The study cohort included 249 patients with PA and 173 with WT. The participants were split into a training set of 316 and a validation set of 106. Six independent predictors were identified: sex, age, smoking history, bilateral parotid involvement, white blood cell (WBC) count, and postprandial blood glucose at 2 hours (PBG2h). The AUC of the nomogram on the training set was 0.951, and the sensitivity, specificity and accuracy were 0.91, 0.906 and 0.908, respectively; on the validation set, these metrics were 0.934, 0.918, 0.844 and 0.887, respectively. The calibration curves were in close alignment with the ideal diagonals, indicating that the model has excellent calibration performance. Significant net clinical benefit was observed in the DCA and CIC analyses when the threshold probabilities were in the range of 0.05 to 0.97 for the training set and 0.07 to 0.96 for the validation set. Conclusion This study presents the first nomogram model integrating clinical features and biochemical indicators for preoperative differentiation between PA and WT. The model offers an accurate, cost-effective tool to support personalized treatment decisions.
Keywords: Pleomorphic adenoma, Warthin's tumor, differential diagnosis, White blood cell count, metabolic syndrome
Received: 23 Jan 2025; Accepted: 14 Aug 2025.
Copyright: © 2025 Huang, Zhao, He, Su and Zhang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Zhe Zhang, First Affiliated Hospital, Guangxi Medical University, Nanning, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.