BACKGROUND: Few studies have measured ventilation during early cardiopulmonary resuscitation (CPR) before advanced airway placement. Resuscitation guidelines recommend pauses after every 30 chest compressions to deliver ventilations. The effectiveness of bag-valve-mask ventilation delivered during the pause in chest compressions is unknown. We sought to determine: (1) the incidence of lung inflation with bag-valve-mask ventilation during 30:2 CPR; and (2) the association of ventilation with outcomes after out-of-hospital cardiac arrest. METHODS: We studied patients with out-of-hospital cardiac arrest from 6 sites of the Resuscitation Outcomes Consortium CCC study (Trial of Continuous Compressions versus Standard CPR in Patients with Out-of-Hospital Cardiac Arrest). We analyzed patients assigned to the 30:2 CPR arm with ≥2 minutes of thoracic bioimpedance signal recorded with a cardiac defibrillator/monitor. Detectable ventilation waveforms were defined as having a bioimpedance amplitude ≥0.5 Ω (corresponding to ≥250 mL V _T ) and a duration ≥1 s. We defined a chest compression pause as a 3- to 15-s break in chest compressions. We compared the incidence of ventilation and outcomes in 2 groups: patients with ventilation waveforms in <50% of pauses (group 1) versus those with waveforms in ≥50% of pauses (group 2). RESULTS: Among 1976 patients, the mean age was 65 years; 66% were male. From the start of chest compressions until advanced airway placement, mean±SD duration of 30:2 CPR was 9.8±4.9 minutes. During this period, we identified 26 861 pauses in chest compressions; 60% of patients had ventilation waveforms in <50% of pauses (group 1, n=1177), and 40% had waveforms in ≥50% of pauses (group 2, n=799). Group 1 had a median of 12 pauses and 2 ventilations per patient versus group 2, which had 12 pauses and 12 ventilations per patient. Group 2 had higher rates of prehospital return of spontaneous circulation (40.7% versus 25.2%; P <0.0001), survival to hospital discharge (13.5% versus 4.1%; P <0.0001), and survival with favorable neurological outcome (10.6% versus 2.4%; P <0.0001). These associations persisted after adjustment for confounders. CONCLUSIONS: In this study, lung inflation occurred infrequently with bag-valve-mask ventilation during 30:2 CPR. Lung inflation in ≥50% of pauses was associated with improved return of spontaneous circulation, survival, and survival with favorable neurological outcome.

The automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse is the electrocardiogram (ECG). In this study we propose two deep neural network (DNN) architectures to detect pulse using short ECG segments (5 s), i.e., to classify the rhythm into pulseless electrical activity (PEA) or pulse-generating rhythm (PR). A total of 3914 5-s ECG segments, 2372 PR and 1542 PEA, were extracted from 279 OHCA episodes. Data were partitioned patient-wise into training (80%) and test (20%) sets. The first DNN architecture was a fully convolutional neural network, and the second architecture added a recurrent layer to learn temporal dependencies. Both DNN architectures were tuned using Bayesian optimization, and the results for the test set were compared to state-of-the art PR/PEA discrimination algorithms based on machine learning and hand crafted features. The PR/PEA classifiers were evaluated in terms of sensitivity (Se) for PR, specificity (Sp) for PEA, and the balanced accuracy (BAC), the average of Se and Sp. The Se/Sp/BAC of the DNN architectures were 94.1%/92.9%/93.5% for the first one, and 95.5%/91.6%/93.5% for the second one. Both architectures improved the performance of state of the art methods by more than 1.5 points in BAC.

Early recognition of ventricular fibrillation (VF) and electrical therapy are key for the survival of out-of-hospital cardiac arrest (OHCA) patients treated with automated external defibrillators (AED). AED algorithms for VF-detection are customarily assessed using Holter recordings from public electrocardiogram (ECG) databases, which may be different from the ECG seen during OHCA events. This study evaluates VF-detection using data from both OHCA patients and public Holter recordings. ECG-segments of 4-s and 8-s duration were analyzed. For each segment 30 features were computed and fed to state of the art machine learning (ML) algorithms. ML-algorithms with built-in feature selection capabilities were used to determine the optimal feature subsets for both databases. Patient-wise bootstrap techniques were used to evaluate algorithm performance in terms of sensitivity (Se), specificity (Sp) and balanced error rate (BER). Performance was significantly better for public data with a mean Se of 96.6%, Sp of 98.8% and BER 2.2% compared to a mean Se of 94.7%, Sp of 96.5% and BER 4.4% for OHCA data. OHCA data required two times more features than the data from public databases for an accurate detection (6 vs 3). No significant differences in performance were found for different segment lengths, the BER differences were below 0.5-points in all cases. Our results show that VF-detection is more challenging for OHCA data than for data from public databases, and that accurate VF-detection is possible with segments as short as 4-s.

Early defibrillation by an automated external defibrillator (AED) is key for the survival of out-of-hospital cardiac arrest (OHCA) patients. ECG feature extraction and machine learning have been successfully used to detect ventricular fibrillation (VF) in AED shock decision algorithms. Recently, deep learning architectures based on 1D Convolutional Neural Networks (CNN) have been proposed for this task. This study introduces a deep learning architecture based on 1D-CNN layers and a Long Short-Term Memory (LSTM) network for the detection of VF. Two datasets were used, one from public repositories of Holter recordings captured at the onset of the arrhythmia, and a second from OHCA patients obtained minutes after the onset of the arrest. Data was partitioned patient-wise into training (80%) to design the classifiers, and test (20%) to report the results. The proposed architecture was compared to 1D-CNN only deep learners, and to a classical approach based on VF-detection features and a support vector machine (SVM) classifier. The algorithms were evaluated in terms of balanced accuracy (BAC), the unweighted mean of the sensitivity (Se) and specificity (Sp). The BAC, Se, and Sp of the architecture for 4-s ECG segments was 99.3%, 99.7%, and 98.9% for the public data, and 98.0%, 99.2%, and 96.7% for OHCA data. The proposed architecture outperformed all other classifiers by at least 0.3-points in BAC in the public data, and by 2.2-points in the OHCA data. The architecture met the 95% Sp and 90% Se requirements of the American Heart Association in both datasets for segment lengths as short as 3-s. This is, to the best of our knowledge, the most accurate VF detection algorithm to date, especially on OHCA data, and it would enable an accurate shock no shock diagnosis in a very short time.