ABSTRACT
BACKGROUND: Coronary perfusion pressure (CPP) indicates spontaneous return of circulation and is recommended for high-quality cardiopulmonary resuscitation (CPR). This study aimed to investigate a method for non-invasive estimation of CPP using electrocardiography (ECG) and photoplethysmography (PPG) during CPR. METHODS: Nine pigs were used in this study. ECG, PPG, invasive arterial blood pressure (ABP), and right atrial pressure (RAP) signals were simultaneously recorded. The CPPs were estimated using three datasets: (a) ECG, (b) PPG, and (c) ECG and PPG, and were compared with invasively measured CPPs. Four machine-learning algorithms, namely support vector regression, random forest (RF), K-nearest neighbor, and gradient-boosted regression tree, were used for estimation of CPP. RESULTS: The RF model with a combined ECG and PPG dataset achieved better estimation of CPP than the other algorithms. Specifically, the mean absolute error was 4.49 mmHg, the root mean square error was 6.15 mm Hg, and the adjusted R2 was 0.75. A strong correlation was found between the non-invasive estimation and invasive measurement of CPP (r = 0.88), which supported our hypothesis that machine-learning-based analysis of ECG and PPG parameters can provide a non-invasive estimation of CPP for CPR. CONCLUSIONS: This study proposes a novel estimation of CPP using ECG and PPG with machine-learning-based algorithms. Non-invasively estimated CPP showed a high correlation with invasively measured CPP and may serve as an easy-to-use physiological indicator for high-quality CPR treatment.
ABSTRACT
Ventilation is an important part of cardiopulmonary resuscitation (CPR). The advanced airway mode and 30:2 mode are used for intubated and non-intubated patients, respectively. It is debatable that passive produced by 30 compressions can provide adequate tidal volume for 30:2 mode. In addition, the fragmented ventilation caused by continuous compression may result in ineffective ventilation. In the study, one pig was anaesthetized and intubated for 2 CPRs. Continuous chest compressions with ventilation and continuous chest compressions without mechanical ventilation were performed in 2 CPRs, respectively. Three 10-minute data segments including a period of normal ventilation (V segment), a period of only compressions without ventilation (C segment), and a period of compressions with ventilation (C-V segment) were used to analyze peek flow (PF), peek pressure (PP) and tidal volume. All the data was presented as mean ± standard deviation. Chest compression resulted in 14.90% increase in mean PP (2401.40 ± 94.75 Pa vs 2822.06 ± 291.10 Pa, p<0.05), 81.46% increase in average PF (319.58 ± 56.93 ml/s vs 579.92 ± 80.27 ml/s, p<0.05). The mean tidal volumes for C segment, V segment and C-V segment were 189.13 ml, 514.72 ml, and 429.26ml, respectively. Continuous compressions reduced the accumulative tidal volume, but when five compressions were made in one inspiratory phase, there is almost no loss of tidal volume (510.86 ± 47.24 ml vs 514.72 ± 29.25 ml, p<0.05). The study suggested the ventilator without feedback regulation might reduce the peek pressure during CPR and 5 compressions in 2 s inspiratory phase provided higher tidal volume.Clinical Relevance- This study shows that 150 chest compressions per minute provided greater tidal volume than 100 and 120 compressions per minute; continuous chest compressions could also provide a certain amount of oxygen supply.
