Postoperative recurrence prediction model for perianal abscess using machine learning algorithms
The machine learning-based model effectively identifies patients at high risk of recurrence after perianal abscess surgery. The CatBoost model achieved the best predictive performance, while SHAP analysis enhanced interpretability, supporting individualized patient management.
Authors
- Zheng Zheng (ORCID: https://orcid.org/0000-0001-5221-3209)
- Shaohua Huangfu
- Zhiran Li
- Chungen Zhou
- Ao Chen (ORCID: https://orcid.org/0000-0002-8292-7314)
- Dawei Wang (ORCID: https://orcid.org/0000-0002-6151-5839)
- Caixia Zhang (ORCID: https://orcid.org/0000-0003-1312-5171)
- Yuan Fang (ORCID: https://orcid.org/0009-0009-6968-3739)
- Bin Jiang (ORCID: https://orcid.org/0000-0002-4622-9703)
- Qizhi Liu
Institutions
- Nanjing University of Chinese Medicine (CN)
- Chinese Academy of Medical Sciences & Peking Union Medical College (CN)
- Guang’anmen Hospital (CN)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-12-04
- DOI
- https://doi.org/10.3389/fpubh.2025.1722109
- Primary Topic
- Anorectal Disease Treatments and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China