Perioperative medicine & outcomes
Predicting patient care pathway deviations and their consequences in anaesthesia using machine learning
Authors' conclusion
Machine learning applied to routinely collected data can identify patients at risk of deviating from their intended day-case pathway with stable performance and the potential for clinical usefulness.
Study context
- Population
- Consecutive ambulatory anaesthesia procedures, Belgian network
- Participants
- 51,112 procedures
- Comparison
- Seven machine-learning algorithms for predicting unplanned admission
- Outcome
- Unplanned admission after day-case surgery
Methodological detailsmachine learning, training, validation and test sets, SMOTENC on training data
- Machine learning
- Training, validation and test sets
- SMOTENC on training data
Performance
As reported in the abstract
Prediction of unplanned admission
| Test or model | AUC | Average precision | F1-score |
|---|---|---|---|
| Explainable boosting machine (EBM) | 0.826 | 0.472 | 0.392 |
| Logistic regression | 0.595 | — not stated in the abstract | — not stated in the abstract |
AUC
Explainable boosting machine (EBM)0.826
Logistic regression0.595
Average precision
Explainable boosting machine (EBM)0.472
Logistic regression— not stated in the abstract
F1-score
Explainable boosting machine (EBM)0.392
Logistic regression— not stated in the abstract
— not stated in the abstract
- Unplanned admission incidence
- 9.08%
Original publication
Predicting patient care pathway deviations and their consequences in anaesthesia using machine learning. J Clin Monit Comput. Published 8 September 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →