Machine learning-based prediction of postoperative mortality risk after abdominal surgery
Nomogram, random-forest, gradient-boosting tree, and support vector machine models all demonstrate strong performances for the prediction of postoperative mortality and can be selected based on the clinical circumstances.
Authors
- Yongmei Jin (ORCID: https://orcid.org/0000-0001-5180-4883)
- J Xiang
- Bin Zhao (ORCID: https://orcid.org/0000-0001-5360-6725)
- Yumin Zhong (ORCID: https://orcid.org/0000-0002-0164-8752)
- Shuangshuang Li (ORCID: https://orcid.org/0000-0002-5885-3706)
- Jihong Yuan (ORCID: https://orcid.org/0000-0003-2789-4334)
- S. Zhang (ORCID: https://orcid.org/0000-0001-5850-9502)
Institutions
- Shanghai University of Traditional Chinese Medicine (CN)
- People's Liberation Army 401 Hospital (CN)
- Shanghai Traditional Chinese Medicine Hospital (CN)
- Seventh People's Hospital of Shanghai (CN)
- Community Health Center (US)
Publication Details
- Journal
- World Journal of Gastrointestinal Surgery
- Published
- 2025-03-29
- DOI
- https://doi.org/10.4240/wjgs.v17.i4.103696
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00