Enhanced preoperative prediction of pancreatic fistula using radiomics and clinical features with SHAP visualization
The proposed CR-POPF prediction model based on the XGBoost predictor with the combination of the radiomics and clinical features selected by Lasso regression and RF can effectively predicting the CR-POPF and may provide strong support for early clinical management of CR-POPF.
Authors
- Zhongjun Wu (ORCID: https://orcid.org/0000-0002-1627-0633)
- Kang Zong
- Yanyao Liu
- Baoyong Zhou (ORCID: https://orcid.org/0000-0002-8022-982X)
- Yan Li (ORCID: https://orcid.org/0000-0001-7864-2052)
- Yin Zhou (ORCID: https://orcid.org/0000-0001-6872-6631)
- Yuan Sun (ORCID: https://orcid.org/0000-0002-4529-2815)
Institutions
- The Affiliated Yongchuan Hospital of Chongqing Medical University (CN)
- Chongqing Medical University (CN)
Publication Details
- Journal
- Frontiers in Bioengineering and Biotechnology
- Published
- 2025-04-04
- DOI
- https://doi.org/10.3389/fbioe.2025.1510642
- Primary Topic
- Pancreatic and Hepatic Oncology Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Chongqing Medical University
- Natural Science Foundation of Chongqing
- Centre Scientifique et Technique du Bâtiment