Perioperative medicine & outcomes
Developing a machine learning-based prediction model for postinduction hypotension
Authors' conclusion
The ML-based model demonstrated significant predictive capability for PIH, identifying key clinical predictors.
Study context
- Population
- Adults undergoing non-obstetric surgery under GA with intravenous induction
- Participants
- 20,309 adults
- Outcome
- Occurrence of postinduction hypotension (PIH; Mean arterial pressure (MAP) < 55 mmHg)
- Follow-up
- Within 10 min post-induction
Methodological detailsmachine learning prediction model development and validation, k-fold cross-validation
- Machine learning prediction model development and validation
- K-fold cross-validation
Main finding
As reported in the abstract
PIH incidence and ML model performance
Postinduction hypotension (PIH) occurred
4,948 patients
24.4%
Machine learning (ML) model AUC for predicting PIH
0.732
Observational data: associations, not effects.
Original publication
Developing a machine learning-based prediction model for postinduction hypotension. J Clin Monit Comput. Published 5 May 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →