A CTCs-based recurrence model for non-metastatic renal cell carcinoma: integrating machine learning and SHAP interpretation
Over a median follow-up of 41 months, 24 patients experienced recurrence, while 100 remained recurrence-free. The Random Forest model demonstrated superior performance, achieving a training AUC of 0.84 and a validation AUC of 0.77. SHAP analysis identified key predictors, including pT stage, tumor size, and changes in mesenchymal and hybrid CTC counts.
Authors
- Geng Tian (ORCID: https://orcid.org/0000-0001-5752-4436)
- Tie Chong (ORCID: https://orcid.org/0000-0002-2035-6544)
- Zihao Li (ORCID: https://orcid.org/0000-0002-4040-8188)
- Xiaoyong Chen (ORCID: https://orcid.org/0000-0002-6817-6630)
- Zhenlong Wang (ORCID: https://orcid.org/0000-0002-2287-7028)
- Chia-Sheng Yan
- Delai Fu
- Fabrice Kayitare
Institutions
- Second Affiliated Hospital of Xi'an Jiaotong University (CN)
Publication Details
- Journal
- Biomarkers in Medicine
- Published
- 2025-11-02
- DOI
- https://doi.org/10.1080/17520363.2025.2590789
- Primary Topic
- Renal cell carcinoma treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00