Perioperative medicine & outcomes
A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery
Authors' conclusion
The postoperative admission warning model constructed in this study can effectively predict the probability of patients being admitted to the ICU after surgery, providing a corresponding management tool for postoperative care in surgical patients.
Study context
- Population
- Surgical patients in the VitalDB database
- Exposure
- Logistic regression vs random forest vs support vector machine vs multi-layer perceptron
- Outcome
- Postoperative ICU admission
Methodological detailsretrospective database (VitalDB), machine learning, LASSO regression and random forest variable selection, nomogram
- Retrospective database (VitalDB)
- Machine learning
- LASSO regression and random forest variable selection
- Nomogram
Main finding
As reported in the abstract
Prediction of postoperative ICU admission
| Group | ROC AUC |
|---|---|
| Logistic regression | 0.925 |
Logistic regression
ROC AUC0.925
Observational data: associations, not effects.
Original publication
A warning model for predicting patient admissions to the intensive care unit (ICU) following surgery. Perioper Med (Lond). Published 2 June 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →