No abstract

No abstract

Pulseless electrical activity (PEA) is one of the most common rhythms during a cardiac arrest (CA), and it consists in lack of palpable pulse in presence of electrical activity in the heart. The main treatment for a CA is the cardiopulmonary resuscitation (CPR), including chest compressions and ventilations, together with defibrillation shocks and drugs when necessary. The therapy of PEA depends on its characteristics, mainly the morphology of the QRS complex. Well known algorithms for QRS complex detection and delineation were designed for hemodynamically stable patients with pulsed rhythm (PR). The aim of this study was to develop an automatic method for QRS complex detection in patients with PEA during CA. The database for this study consists of 5128 PEA segments from 264 in-hospital CA patients. The ECG signal was decomposed using the stationary wavelet transform, a peak detector was applied on the third detail component and a multicomponent verification was set to detect the peaks. Finally, a time alignment of the detected QRS complexes was performed using the original ECG signal. The proposed method presents median (IQR) Se/PPV/F1 values of 92.4(15.2)/88.5(15.4)/88.8(15.6) for PEA segments.

Background: Pulseless electrical activity (PEA) is the most common rhythm during in-hospital cardiac arrest (IHCA) with a prevalence around 50%. Knowing the prognosis of PEA evolution towards return of spontaneous circulation (ROSC) could help optimizing both resuscitation maneuvers and pharmacological therapy. The aim of this study was to develop an automatic method to predict the evolution of PEA during resuscitation based on the ECG-waveform. Materials and Methods: The dataset consists of 164 IHCA cases recorded by St. Olav University Hospital (Norway), Hospital of the University of Pennsylvania (USA) and Penn Presbyterian Medical Center (USA). ROSC was verified in 108 cases of the patients by physicians and bioengineers based on episode waveforms and clinical data. PEA segments of 5 sec were extracted from the last 10 min before ROSC or the end of resuscitation therapy. Three machine learning models were designed for segment binary classification based on an SVM (Gaussian) model using: 1) ECG-waveform features (9); 2) QRS-features (8); and 3) both ECG-waveform and QRS-features (17). Ten-fold cross validation was applied to train and test the models, and the performance was given in terms of area under the curve (AUC), sensitivity (Se) to correctly detect cases evolving to ROSC, specificity (Sp) and balanced accuracy (BAC). Results: A total of 780 segments were extracted (472 with ROSC). The median (IQR) for the models with the best feature combination are shown in the Table. The most important ECG-waveform features are associated to the ECG spectral distribution. QRS features that showed relevant information about the evolution of PEA were heart rate median and standard deviation, and QRS width, slope and amplitude. Conclusions: ROSC/no ROSC prediction of PEA segments is feasible using ECG signal information. The combination of ECG-waveform and QRS features enhances performance of predictive model.

Introduction: PEA is commonly observed in in-hospital cardiac arrest. ROSC is currently the only indication of treatment response. Studies suggest that QRS duration (QRSd) and heart rate (HR) develop differently in patients who obtain ROSC or not. The aim of this study was to assess prospectively how QRSd and HR affect the immediate outcome of patients with PEA. Method: We investigated 327 episodes of IHCA in 298 patients, collected at two US and one Norwegian hospital. We assessed the ECG in 559 segments of PEA, measuring QRSd and HR in pauses of compressions, and noted the clinical state that followed PEA. We investigated the development of HR, QRSd, and transitions to ROSC or noROSC in a joint linear mixed/ time-to-event model, using software R version 4.0.3 with the package ‘JMbayes2’. Results: A HR increase by 50bpm increased the intensity (“hazard”) of gaining ROSC by 42% (p<0.01), and a 50ms decrease in QRSd increased the intensity of gaining ROSC by 29% (p<0.01). A decreasing HR had no significant impact; however, if QRSd increased by 50ms this increased the probability of transitioning to other lethal states (ventricular tachycardia or fibrillation, asystole, or death) by 24% (p<0.01). Still, several patients experienced increasing QRSd before obtaining ROSC. The figure shows an example of how QRSd (lower left) and HR (upper left) developed in one PEA segment overlaid the linear model (blue line). The estimated probability of obtaining ROSC (green line with 95% CI) or transitioning to other arrest states (red line) over the next 4 minutes are displayed to the right. This patient obtained ROSC at approx. 7min. Conclusion: HR and QRSd conveys information of the immediate outcome (ROSC/noROSC) in PEA. This may guide the team in their efforts, and possibly allow for individual tailoring of treatment, e.g., by delaying a (potentially harmful) epinephrine administration. Due to low specificity, the model cannot support termination of resuscitation.