An interpretable machine learning model integrating computed tomography radiomics and clinical features for predicting the urosepsis after percutaneous nephrolithotomy
This study constructed a predictive model that incorporates clinical risk characteristics and radiomics scores to assess the risk of urosepsis after PCNL, with SHAP visualization for clinical physicians to formulate evaluation strategies.
Authors
- Haoxiang Xu (ORCID: https://orcid.org/0000-0002-5047-5341)
- Xiaofu Qiu
- Kaiqiang Wang (ORCID: https://orcid.org/0000-0003-0142-2646)
- Xiaoming Zhang (ORCID: https://orcid.org/0000-0002-9732-7450)
- Yuansong Xiao
- Qi Fu (ORCID: https://orcid.org/0000-0002-1626-0419)
- Zhi Cao (ORCID: https://orcid.org/0000-0002-9735-0255)
- Chenglin Yang (ORCID: https://orcid.org/0000-0002-0834-5164)
- Yue Yang (ORCID: https://orcid.org/0000-0002-3700-7420)
- Wei Wang (ORCID: https://orcid.org/0000-0002-9679-9480)
- Shengtao Zeng
Institutions
- Third Affiliated Hospital of Southern Medical University (CN)
- Guangdong Provincial People's Hospital (CN)
- Southern Medical University (CN)
Publication Details
- Journal
- BioMedical Engineering OnLine
- Published
- 2025-10-21
- DOI
- https://doi.org/10.1186/s12938-025-01460-y
- Citations
- 1
- Primary Topic
- Kidney Stones and Urolithiasis Treatments
- Type
- article
- Field-Weighted Citation Impact
- 1.52