A machine learning model significantly improves risk stratification for post-pancreaticoduodenectomy hemorrhage (pph), identifying eight key predictors such as albumin levels and operative time. With an area under the curve (AUC) of 0.84 during training and 0.82 in validation, this model outperformed traditional logistic regression, enabling clinicians to classify patients into low, medium, and high-risk groups effectively. The deployment of this model as an interactive tool aids in the proactive management of at-risk patients.
Validation Study by Zhang Z, Zhao X (…) Gu Z et 5 al. in BMJ Open
© Author(s) (or their employer(s)) 2025. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ Group.