Perioperative medicine & outcomes
A machine learning approach to predicting early and late postoperative reintubation
Authors' conclusion
The scoring systems developed from the logistic regression models demonstrated strong performance in terms of both accuracy and discrimination across the different POR outcomes (Average Brier score, 0.172; Average c-statistic, 0.852).
Study context
- Population
- Surgical patients in the American College of Surgeons (ACS) National Surgical Quality Improvement Program (NSQIP) database
- Exposure
- Scoring systems vs Full set of risk variables
- Outcome
- Prediction of combined, early (within 72 h) and late (within 30 days) postoperative reintubation (POR)
Methodological detailsmachine learning, registry data (ACS NSQIP)
- Machine learning
- Registry data (ACS NSQIP)
Main finding
As reported in the abstract
Accuracy and discrimination across POR outcomes
| Group | Average Brier score | Average c-statistic |
|---|---|---|
| Scoring systems | 0.172 | 0.852 |
| Full set of risk variables | 0.145 | 0.870 |
Average Brier score
Scoring systems0.172
Full set of risk variables0.145
Average c-statistic
Scoring systems0.852
Full set of risk variables0.870
Observational data: associations, not effects.
Original publication
A machine learning approach to predicting early and late postoperative reintubation. J Clin Monit Comput. Published 3 September 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →