Perioperative medicine & outcomes
Developing and validating a machine learning ensemble model to predict postoperative delirium in a cohort of high-risk surgical patients: A secondary cohort analysis
Authors' conclusion
A predictive model composed of three indicative readily available features performed better than those with numerous perioperative features, pointing to its feasibility as a prognostic tool for POD.
Study context
- Population
- Inpatients with all-cause postoperative 30-day mortality risk >5% (ExCare Model), 800-bed quaternary university teaching hospital, Southern Brazil, September 2015 to February 2020
- Participants
- 1,453 inpatients
- Comparison
- 52 preoperative vs 60 postoperative vs Three features
- Primary endpoint
- Incidence of POD (Confusion Assessment Method); model performance compared by AUC
- Follow-up
- Up to 7 days postoperatively
Methodological detailsmachine-learning ensemble prediction model, nested cross-validation, single-centre
- Machine-learning ensemble prediction model
- Nested cross-validation
- Single-centre
Primary result
As reported in the abstract
POD incidence and model AUC
Cumulative incidence of delirium
117
Absolute risk of postoperative delirium (POD) per 100 patients
8.05
Original publication
Developing and validating a machine learning ensemble model to predict postoperative delirium in a cohort of high-risk surgical patients: A secondary cohort analysis. Eur J Anaesthesiol. Published 1 March 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →