Development and validation of interpretable machine learning models for predicting the risk of necrosis after finger replantation: A retrospective multicenter study
An interpretable machine-learning model based on complete blood counts and related inflammatory marker levels was constructed and validated to predict the likelihood of developing DN following finger replantation. This model can assist clinicians in the prompt identification of high-risk patients post-replantation, enabling timely intervention.
Authors
- Shengzhe Liu (ORCID: https://orcid.org/0000-0002-7746-233X)
- Guiyang Wang (ORCID: https://orcid.org/0000-0001-7380-6783)
- Yucheng Liu (ORCID: https://orcid.org/0009-0007-2396-8224)
- Yan Zhang (ORCID: https://orcid.org/0000-0001-5738-9537)
- Chenglong Wu (ORCID: https://orcid.org/0000-0002-5198-4906)
- Shi Wang (ORCID: https://orcid.org/0000-0001-8018-4345)
- Jihui Ju (ORCID: https://orcid.org/0000-0003-4462-8134)
- Yang Cao (ORCID: https://orcid.org/0000-0001-8636-7919)
- Shuai Dong (ORCID: https://orcid.org/0000-0002-2434-2430)
- Kai Wang (ORCID: https://orcid.org/0000-0001-9705-6366)
- Xinwei Hou
Institutions
- Soochow University (CN)
- Ruihua Affiliated Hospital of Soochow University (CN)
- Jiangsu Shengze Hospital (CN)
Publication Details
- Journal
- Injury
- Published
- 2025-11-20
- DOI
- https://doi.org/10.1016/j.injury.2025.112893
- Primary Topic
- Reconstructive Surgery and Microvascular Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00