Cardiac arrest & resuscitation
Cycle-to-Cycle Prediction of Return of Spontaneous Circulation Using End-Tidal Carbon Dioxide Dynamics in Out-of-Hospital Cardiac Arrest
Authors' conclusion
Sequential EtCO2 dynamics showed good event-level discrimination for predicting ROSC in the subsequent cycle. When applied at each cycle, the model retained modest discrimination but overestimated ROSC probability, indicating that recalibration is required before cycle-to-cycle use.
Study context
- Population
- Adult out-of-hospital cardiac arrest (OHCA) patients from the NTUH-HYCARD database between 2016 and 2023patients, 1,651 event-level EtCO2 sequences
- Participants
- 1,480 patientsEvents: 583 events ended with return of spontaneous circulation (ROSC)
- Predictors
- Sequential EtCO2 values
- Predicted outcome
- ROSC in the subsequent 2-minute resuscitation cycle
Methodological detailsdevelopment and internal validation, 10-fold cross-validation
- Development and internal validation
- 10-fold cross-validation
Model performance
As reported in the abstract
ROSC in the subsequent 2-minute resuscitation cycle
AUROC
ROSC in the subsequent cycle (event level)
0.876(95% CI, 0.863-0.890)
Cycle level, 17,029 prediction points; ROSC prevalence, 3.4%
0.685(95% CI, 0.664-0.706)
Brier score
0.140
95% CI 0.131–0.149
Further findings
ROSC in the subsequent cycle (cycle level, 17,029 prediction points; ROSC prevalence, 3.4%) · subsequent 2-minute resuscitation cycle
- Brier score
- 0.285; 95% CI, 0.268-0.303
- Model systematically overestimated ROSC probability
Original publication
Cycle-to-Cycle Prediction of Return of Spontaneous Circulation Using End-Tidal Carbon Dioxide Dynamics in Out-of-Hospital Cardiac Arrest. Resuscitation. Published 12 November 2026. doi:10. 1016/ j. resuscitation. 2026. 111387
Composed by AI from the published abstract and checked against it. How Briefs are made →