ORIGINAL RESEARCH article
Front. Endocrinol.
Sec. Thyroid Endocrinology
Volume 16 - 2025 | doi: 10.3389/fendo.2025.1655828
This article is part of the Research TopicExploring the Applications of Artificial Intelligence in Disease Screening, Diagnosis, Treatment, and NursingView all 13 articles
Prediction of malignancy risk in Bethesda III nodules: development and validation of multiple machine learning models
Provisionally accepted
Wentian Li1,2
Jiayu Zhu2Ying Wang1,2Jingxiu Li1,2Zhonghui Li2Cuicui Wang2Jingli Xue2
Peng Zhou2*Qingqing He2*- 1Shandong First Medical University, Jinan, China
- 2960th Hospital of People's Liberation Army Joint Logistic Support Force, Jinan, 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
Objective: To develop and validate a machine learning (ML)-based prediction model of Bethesda III nodules and create a nomogram based on the best model. Methods: We collected data on patients with Bethesda III nodules who were admitted between January 2020 and June 2024, including 276 Bethesda III nodules from 7371 patients who underwent ultrasound-guided fine needle aspiration (US-FNA). Clinical, ultrasonographic, cytological, laboratory, and molecular data were collected and randomly split into training and validation cohorts at a ratio of 7: 3. Six feature selection methods and ML algorithms—Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)—were evaluated. A nomogram was then created based on the best-performing model. Results: The study cohort included 276 Bethesda III nodules with a final malignancy rate of 65.2% (180/276). LR exhibited the highest area under the receiver operating characteristic (ROC) curve (AUC: 0.823) in cross-validation of the validation set. Additionally, the calibration curves and Decision Curve Analysis (DCA) results were also favorable. The model included BRAF, composition, shape, orientation, and the thyroid imaging reporting and data system (TI-RADS). The nomogram exhibited robust discrimination (AUC: 0.846 in the validation set), calibration, and clinical applicability across the two datasets after 500 bootstraps. Conclusion: Among the six ML algorithms, the LR algorithm demonstrated the best performance. A nomogram was developed to predict the malignancy risk in Bethesda III nodules. This nomogram may serve as a valuable tool to reduce diagnostic uncertainty and provide personalized risk stratification for patients.
Keywords: thyroid nodules, Risk of malignancy, Atypia of undetermined significance, machine learning, Prediction model
Received: 28 Jun 2025; Accepted: 18 Aug 2025.
Copyright: © 2025 Li, Zhu, Wang, Li, Li, Wang, Xue, Zhou and He. 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:
Peng Zhou, 960th Hospital of People's Liberation Army Joint Logistic Support Force, Jinan, China
Qingqing He, 960th Hospital of People's Liberation Army Joint Logistic Support Force, Jinan, 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.