Construct validation of machine learning models for predicting surgical site infection risk following ankle fracture surgery
The findings of this study demonstrate that modern ML methods offer high predictive accuracy for SSI risk, with the GBM model outperforming the traditional logistic regression model. This study provides strong evidence for the clinical application of ML-based risk assessment, suggesting that integrating preoperative risk factors with ML techniques can enable more precise, individualized treatment strategies for the prevention and management of SSI.
Authors
- Chen Guo-lin (ORCID: https://orcid.org/0009-0001-3056-8145)
- Chengqiang Zhou (ORCID: https://orcid.org/0000-0001-6907-1163)
- Wei Huang (ORCID: https://orcid.org/0000-0002-5862-3126)
- Gang Wu (ORCID: https://orcid.org/0000-0001-8941-2500)
- Leilei Qin (ORCID: https://orcid.org/0000-0002-9443-7080)
- Qinyang Zhang
- Chen Li (ORCID: https://orcid.org/0000-0001-6249-8957)
- Ning Hu (ORCID: https://orcid.org/0000-0002-6444-8467)
- Youliang Shen (ORCID: https://orcid.org/0000-0002-9247-0290)
- Feilong Li (ORCID: https://orcid.org/0000-0002-7198-3919)
- Jianye Yang (ORCID: https://orcid.org/0000-0001-5172-1068)
Institutions
- Nantong University (CN)
- People's Hospital of Kaizhou District (CN)
- The Affiliated Taizhou People's Hospital of Nanjing Medical University (CN)
- The Affiliated Yongchuan Hospital of Chongqing Medical University (CN)
- Taizhou University (CN)
- Nanjing Medical University (CN)
- Chongqing Medical University (CN)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2025-10-07
- DOI
- https://doi.org/10.1097/js9.0000000000003239
- Citations
- 2
- Primary Topic
- Clinical practice guidelines implementation
- Type
- article
- Field-Weighted Citation Impact
- 3.76