Advancing postoperative mortality prediction in gastrectomy: a machine learning approach using NSQIP data
The XGBoost model demonstrated the highest predictive performance for 30-day postoperative mortality following gastrectomy. Preoperative laboratory variables and age were key predictors. Incorporating ML-based models into clinical practice has the potential to enhance perioperative decision-making and improve patient outcomes after gastrectomy.
Authors
- Suman Niranjan (ORCID: https://orcid.org/0000-0002-8149-131X)
- Chan Shen (ORCID: https://orcid.org/0000-0001-5680-3134)
- Shouhao Zhou (ORCID: https://orcid.org/0000-0002-8124-5047)
- Dong-Won Kang (ORCID: https://orcid.org/0000-0002-7088-867X)
- Charles C. Vining (ORCID: https://orcid.org/0000-0001-6665-4064)
- Chanhyun Park (ORCID: https://orcid.org/0000-0002-1081-0950)
- Abhinandan Chowdhury (ORCID: https://orcid.org/0000-0002-7750-0308)
- Colette R. Pameijer (ORCID: https://orcid.org/0000-0002-1967-0501)
- Russell Torres
Institutions
- University of North Texas (US)
- Pennsylvania State University (US)
- Chosun University (KR)
- Savannah State University (US)
- Decision Sciences (United States) (US)
- Penn State Milton S. Hershey Medical Center (US)
- The University of Texas at Austin (US)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2025-10-14
- DOI
- https://doi.org/10.1097/js9.0000000000003688
- Primary Topic
- Gastric Cancer Management and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 0.00