Cardiac arrest & resuscitation
Early stratification of risk for poor neurological outcome after cardiac arrest is improved with processed EEG data
Authors' conclusion
The combination of early processed EEG and clinical data were best able to stratify neurological risk early after cardiac arrest using machine learning algorithms, but external validation is needed.
Study context
- Population
- Comatose patients in ICU after return of spontaneous circulation (ROSC) following cardiac arrest
- Participants
- 913 patients
- Comparison
- Combined vs Clinical vs EEG (BIS-SR)
- Outcome
- Poor Cerebral Performance Category score (CPC 3-5)
Methodological detailsmachine learning
- Machine learning
Performance
As reported in the abstract
Prediction of poor outcome (CPC 3-5)
| Test or model | AUC poor long-term outcome (6-h data) | AUC poor discharge outcome (6-h data) |
|---|---|---|
| Combined | 0.88 (0.87-0.90) | 0.86 (0.84-0.87) |
Combined
AUC poor long-term outcome (6-h data)0.88 (0.87-0.90)
AUC poor discharge outcome (6-h data)0.86 (0.84-0.87)
- Combined vs Clinical; EEG (BIS-SR): P < 0.001 — combined significantly improved AUC vs either data set alone
Further findings
Poor outcome rate
- Poor outcome at discharge
- 70%
- Poor outcome at long-term assessment
- 72%
Original publication
Early stratification of risk for poor neurological outcome after cardiac arrest is improved with processed EEG data. Resuscitation. Published 14 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →