Triglyceride–glucose index as a key predictor of ARDS in acute pancreatitis: SHAP analysis reveals its critical role in risk stratification
TyG index was associated with in-hospital ARDS in AP. The XGBoost and Random Forest models based on the TyG index had the best performance for predicting ARDS in AP patients. The SHAP method further confirmed that the TyG index serves as a significant predictor for the development of ARDS in patients with acute pancreatitis.
Authors
- Cuirong Guo (ORCID: https://orcid.org/0000-0003-4629-1715)
- Ju Luo (ORCID: https://orcid.org/0000-0002-5595-9513)
- Ning Ding (ORCID: https://orcid.org/0000-0001-5618-6359)
- Yingjie Su (ORCID: https://orcid.org/0000-0001-6566-8755)
- Zhe Chen (ORCID: https://orcid.org/0000-0002-7293-1862)
Institutions
- Central South University (CN)
- Changsha Medical University (CN)
- Changsha Central Hospital (CN)
- University of South China (CN)
Publication Details
- Journal
- Frontiers in Nutrition
- Published
- 2025-11-21
- DOI
- https://doi.org/10.3389/fnut.2025.1662379
- Primary Topic
- Pancreatitis Pathology and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Natural Science Foundation of Hunan Province