Explainable multi-modal machine learning for predicting occult pulmonary metastases in differentiated thyroid cancer: a SHAP-based approach prior to radioactive iodine scans
The logistic model (LR) showed the best performance in predicting occult lung metastases of thyroid cancer patients before <sup>131</sup>I-WBS. Lymph nodes metastases and throglobulin have the most significant impact on the prediction.
Authors
- Jaesik Jeong
- Heqing Yi (ORCID: https://orcid.org/0000-0002-5164-4821)
- Shui Jin
- Youwu Su (ORCID: https://orcid.org/0000-0001-9146-4780)
- Yukun Cai
- Ye Yuan (ORCID: https://orcid.org/0000-0002-8339-0504)
- Xuemei Ye
Institutions
- Chonnam National University (KR)
- Wenzhou Medical University (CN)
- Zhejiang Cancer Hospital (CN)
Publication Details
- Journal
- Frontiers in Medical Technology
- Published
- 2025-11-28
- DOI
- https://doi.org/10.3389/fmedt.2025.1685088
- Primary Topic
- Thyroid Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation
- National Natural Science Foundation of China
- National Research Foundation of Korea
- Ministry of Education, India
- Natural Science Foundation of Zhejiang Province