ICU sedation, delirium & recovery
Application of Machine Learning Models to Biomedical and Information System Signals From Critically Ill Adults
Authors' conclusion
ML-derived notifications for clinically actioned hemodynamic instability and respiratory failure events represent an advance because the magnitude of the differences of accuracy, precision, misclassification rate, and pre-event lead time is large enough to allow more proactive care and has markedly lower frequency and interruption of bedside physician work flows.
Study context
- Population
- Critically ill adults
- Comparison
- Machine learning (ML) notifications vs telemedicine system (TS) alerts vs BM alarms
- Outcome
- Prediction of intubation or vasopressor initiation events
Methodological detailsinternal and external validation, COVID-19 cohort
- Internal and external validation
- COVID-19 cohort
Performance
As reported in the abstract
Accuracy for predicting intubation and vasopressor initiation
| Test or model | Accuracy |
|---|---|
| ML | 0.87-0.94 |
| TS | 0.28-0.53 |
| BM | 0.019-0.028 |
Accuracy
ML0.87-0.94
TS0.28-0.53
BM0.019-0.028
Further findings
External validation and COVID-19 cohorts
- ML performance similar to internal validation cohorts
Parts of this Brief are withheld: the automatic checks could not confirm them against the abstract.
Original publication
Application of Machine Learning Models to Biomedical and Information System Signals From Critically Ill Adults. Chest. Published 1 November 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →