Prediction of malignancy risk in Bethesda III nodules: development and validation of multiple machine learning models
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.
Authors
- Jing‐Xiu Li (ORCID: https://orcid.org/0000-0003-0291-8176)
- Jingli Xue
- Ying Wang (ORCID: https://orcid.org/0000-0003-3212-9653)
- Peng Zhou (ORCID: https://orcid.org/0009-0004-0071-5687)
- Cuicui Wang (ORCID: https://orcid.org/0000-0001-5729-9638)
- Qingqing He (ORCID: https://orcid.org/0000-0002-6019-7664)
- Zhonghui Li (ORCID: https://orcid.org/0000-0003-0591-9350)
- Jiayu Zhu (ORCID: https://orcid.org/0000-0002-2228-9605)
- Wentian Li
Institutions
- Shandong University of Traditional Chinese Medicine (CN)
- People's Liberation Army 401 Hospital (CN)
- Shandong First Medical University (CN)
Publication Details
- Journal
- Frontiers in Endocrinology
- Published
- 2025-08-29
- DOI
- https://doi.org/10.3389/fendo.2025.1655828
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Chinese People’s Liberation Army