CT-based explainable machine learning for predicting benign and malignant thyroid nodules: a multi-center study
The combined model performs better under the LR algorithm. Combined with SHAP explainable analysis, it provides a non-invasive, efficient, and transparent tool for preoperative differentiation of benign and malignant thyroid nodules, potentially optimizing individualized clinical management.
Authors
- Kai Hu
- Tingting Jiang (ORCID: https://orcid.org/0000-0002-6924-7613)
- Tong Chen (ORCID: https://orcid.org/0000-0002-2715-5278)
- Juntao Yang (ORCID: https://orcid.org/0000-0003-1180-391X)
- Tengfei Ke (ORCID: https://orcid.org/0009-0002-7513-4997)
- Manyu Luo (ORCID: https://orcid.org/0000-0002-3081-2793)
- Jing Yang (ORCID: https://orcid.org/0009-0000-1663-6781)
- Qingzhu Gao (ORCID: https://orcid.org/0000-0003-1903-7375)
- Yong Liu (ORCID: https://orcid.org/0000-0003-2138-304X)
- Jun Chen (ORCID: https://orcid.org/0000-0002-3439-0495)
- Bin Yang (ORCID: https://orcid.org/0000-0001-5300-5970)
- Zhanhua Liang (ORCID: https://orcid.org/0000-0001-6483-4758)
- Z. He (ORCID: https://orcid.org/0000-0001-5154-6490)
- Haijun He (ORCID: https://orcid.org/0000-0001-6954-5701)
- Xinyue Zi
Institutions
- Dalian Medical University (CN)
- Kunming Medical University (CN)
- Hua Medicine (China) (CN)
- First Affiliated Hospital of Dalian Medical University (CN)
- Nanchong Central Hospital (CN)
- Dali University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-12-09
- DOI
- https://doi.org/10.3389/fonc.2025.1675943
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Yunnan Provincial Department of Education