Dual-radiomics based on SHapley additive explanations for predicting hematologic toxicity in concurrent chemoradiotherapy patients
Combining radiomic and dosiomic features improves classification performance in predicting HT in patients with advanced cervical cancer undergoing CCRT, with the multi-step SHAP-based feature selection scheme offering additional advantages. These models hold promise for optimizing patient treatment strategies.
Authors
- Wenbin Yan (ORCID: https://orcid.org/0000-0002-3211-7559)
- Xizi Long (ORCID: https://orcid.org/0000-0002-0502-5675)
- Qian Sui (ORCID: https://orcid.org/0000-0002-4667-9675)
- Luqiao Chen
- Qionghui Zhou
- Qianxi Ni (ORCID: https://orcid.org/0000-0003-4085-3430)
- Zhipeng He
- J Liu (ORCID: https://orcid.org/0000-0002-1857-7655)
Institutions
- Central South University (CN)
- The First Hospital of Changsha (CN)
- Hunan Cancer Hospital (CN)
- Xiangya Hospital Central South University (CN)
- University of South China (CN)
Publication Details
- Journal
- Discover Oncology
- Published
- 2025-04-16
- DOI
- https://doi.org/10.1007/s12672-025-02336-2
- Citations
- 3
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 4.08
Funders
- Natural Science Foundation of Hunan Province