Search

Monitoring physiological waveforms, specifically hemodynamic variables (e.g., blood pressure waveforms) and end-tidal CO 2 (EtCO 2 ), during pediatric cardiopulmonary resuscitation (CPR) has been demonstrated to improve survival rates and outcomes when compared to standard depth-guided CPR. However, waveform guidance has largely been based on thresholds for single parameters and therefore does not leverage all the information contained in multimodal data. We hypothesize that the combination of multimodal physiological features improves the prediction of the return of spontaneous circulation (ROSC), the clinical indicator of short-term CPR success. We used machine learning algorithms to evaluate features extracted from eight low-resolution (4 samples per minute) physiological waveforms to predict ROSC. The waveforms were acquired from the 2nd to 10th minute of CPR in pediatric swine models of cardiac arrest (N = 89, 8-12 kg). The waveforms were divided into segments with increasing length (both forward and backward) for feature extraction, and machine learning algorithms were trained for ROSC prediction. For the full CPR period (2nd to 10th minute), the area under the receiver operating characteristics curve (AUC) was 0.93 (95% CI: 0.87-0.99) for the multivariate model, 0.70 (0.55-0.85) for EtCO 2 and 0.80 (0.67-0.93) for coronary perfusion pressure. The best prediction performances were achieved when the period from the 6th to the 10th minute was included. Poor predictions were observed for some individual waveforms, e.g., right atrial pressure. In conclusion, multimodal waveform features carry relevant information for ROSC prediction. Using multimodal waveform features in CPR guidance has the potential to improve resuscitation success and reduce mortality.

Aim: Cardiac arrest often results in severe neurologic injury. Improving care for these patients is difficult as few noninvasive biomarkers exist that allow physicians to monitor neurologic health. The amount of low-frequency power (LFP, 0.01-0.1 Hz) in cerebral haemodynamics has been used in functional magnetic resonance imaging as a marker of neuronal activity. Our hypothesis was that increased LFP in cerebral blood flow (CBF) would be correlated with improvements in invasive measures of neurologic health., Methods: We adapted the use of LFP for to monitoring of CBF with diffuse correlation spectroscopy. We asked whether LFP (or other optical biomarkers) correlated with invasive microdialysis biomarkers (lactate-pyruvate ratio - LPR - and glycerol concentration) of neuronal injury in the 4 h after return of spontaneous circulation in a swine model of paediatric cardiac arrest (Sus scrofa domestica, 8-11 kg, 51% female). Associations were tested using a mixed linear effects model., Results: We found that higher LFP was associated with higher LPR and higher glycerol concentration. No other biomarkers were associated with LPR; cerebral haemoglobin concentration, oxygen extraction fraction, and one EEG metric were associated with glycerol concentration., Conclusion: Contrary to expectations, higher LFP in CBF was correlated with worse invasive biomarkers. Higher LFP may represent higher neurologic activity, or disruptions in neurovascular coupling. Either effect may be harmful in the acute period after cardiac arrest. Thus, these results suggest our methodology holds promise for development of new, clinically relevant biomarkers than can guide resuscitation and post-resuscitation care. Institutional protocol number: 19-001327., (Copyright © 2022. Published by Elsevier B.V.)