Estimating the amplitude spectrum area of ventricular fibrillation during cardiopulmonary resuscitation using only ECG waveform

Abstract

Background: Amplitude spectrum area (AMSA) calculated from ventricular fibrillation (VF) can be used to monitor the effectiveness of chest compression (CC) and optimize the timing of defibrillation.However, reliable AMSA can only be obtained during CC pause because of artifacts. In this study, we sought to develop a method for estimating AMSA during cardiopulmonary resuscitation (CPR) using only the electrocardiogram (ECG) waveform.Methods: Intervals of 8 seconds ECG and CC-related references, including 4 seconds during CC and an adjacent 4 seconds without CC, were collected before 1,008 defibrillation shocks from 512 out-of-hospital cardiac arrest patients. Signal quality was analyzed based on the irregularity of autocorrelation of VF. If signal quality index (SQI) was high, AMSA would be calculated from the original signal. Otherwise, CC-related artifacts would be constructed and suppressed using the least mean square filter from VF before calculation of AMSA. The algorithm was optimized using 480 training shocks and evaluated using 528 independent testing shocks.Results: Overall, CC resulted in lower SQI [0.15 (0.04-0.61) with CC vs. 0.75 (0.61-0.83) without CC, P<0.01] and higher .2) with CC vs. 7.2 (4.9-10.6) mVHz without CC, P<0.01] values.The predictive accuracy (49.2% vs. 66.5%, P<0.01) and area under the receiver operating characteristic curve (AUC) (0.647 vs. 0.734, P<0.01) were significantly decreased during CC. Using the proposed method, the estimated AMSA was 7.1 (5.0-15.2) mVHz, the predictive accuracy was 67.0% and the AUC was 0.713, which were all comparable with those calculated without CC.Conclusions: Using the signal quality-based artifact suppression method, AMSA can be reliably estimated and continuously monitored during CPR.

Real-time amplitude spectrum area estimation during chest compression from the ECG waveform using a 1D convolutional neural network

“…The real-life dataset of corrupted/uncorrupted segment pairs was used to train the model due to the heterogeneity of CPR artifacts in real-life data and homogeneity of CPR artifacts in simulated data. As shown in Table 4 , the performance of the proposed method is demonstrated to be superior to that of the traditional AMSA calculation method using simulated data and independent real-life CPR data ( Zuo et al, 2021 ; Coult et al, 2022 ). Experimental results demonstrated the excellent feature extraction capability to exploit all information reflecting the energy state of the myocardium hidden in the VF signal.…”

Adaptive Recursive Least Squares Denoising in Ventricular Fibrillation ECG Signals

“…[20][21][22][23][24] Combined with the prior knowledge of signal quality and energy, it is convenient to eliminate the adverse effects of chest compressions. [25][26][27] Adaptive denoising approaches are suitable for nonstationary stochastic processes because they can adjust their parameters automatically, and require little or no prior knowledge about the signals and noises.…”