Cardiac arrest & resuscitation
Prediction of blood pressure using chest compression waveform during cardiopulmonary resuscitation
Authors' conclusion
Blood pressure generated by chest compressions can be predicted with high accuracy by a machine learning method using chest compression waveform information obtained from a CPR feedback device and the patient's demographic characteristics.
Study context
- Population
- Patients with cardiac arrest during CPR with arterial cannulation14,619 datasets
- Participants
- 19 patients
- Comparison
- Predicted vs measured BP during CPR
- Outcome
- Correlation between predicted BP (from chest compression waveform of a CPR feedback device) and actual BP
Methodological detailsmachine learning (optimized Gaussian process regression), 41 features selected by neighborhood component analysis
- Machine learning (optimized Gaussian process regression)
- 41 features selected by neighborhood component analysis
Performance
As reported in the abstract
Correlation (r) between predicted and actual BP
- SBP r = 0.954 (95% CI 0.951-0.957)
- p < 0.001
- DBP r = 0.926 (95% CI 0.921-0.931)
- p < 0.001
- MBP r = 0.958 (95% CI 0.955-0.961)
- p < 0.001
Original publication
Prediction of blood pressure using chest compression waveform during cardiopulmonary resuscitation. Resuscitation. Published 23 July 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →