Automated Condition-Based Suppression of the CPR Artifact in ECG Data to Make a Reliable Shock Decision for AEDs during CPR

Abstract

Cardiopulmonary resuscitation (CPR) corrupts the morphology of the electrocardiogram (ECG) signal, resulting in an inaccurate automated external defibrillator (AED) rhythm analysis. Consequently, most current AEDs prohibit CPR during the rhythm analysis period, thereby decreasing the survival rate. To overcome this limitation, we designed a condition-based filtering algorithm that consists of three stop-band filters which are turned either ‘on’ or ‘off’ depending on the ECG’s spectral characteristics. Typically, removing the artifact’s higher frequency peaks in addition to the highest frequency peak eliminates most of the ECG’s morphological disturbance on the non-shockable rhythms. However, the shockable rhythms usually have dynamics in the frequency range of (3–6) Hz, which in certain cases coincide with CPR compression’s harmonic frequencies, hence, removing them may lead to destruction of the shockable signal’s dynamics. The proposed algorithm achieves CPR artifact removal without compromising the integrity of the shockable rhythm by considering three different spectral factors. The dataset from the PhysioNet archive was used to develop this condition-based approach. To quantify the performance of the approach on a separate dataset, three performance metrics were computed: the correlation coefficient, signal-to-noise ratio (SNR), and accuracy of Defibtech’s shock decision algorithm. This dataset, containing 14 s ECG segments of different types of rhythms from 458 subjects, belongs to Defibtech commercial AED’s validation set. The CPR artifact data from 52 different resuscitators were added to artifact-free ECG data to create 23,816 CPR-contaminated data segments. From this, 82% of the filtered shockable and 70% of the filtered non-shockable ECG data were highly correlated (>0.7) with the artifact-free ECG; this value was only 13 and 12% for CPR-contaminated shockable and non-shockable, respectively, without our filtering approach. The SNR improvement was 4.5 ± 2.5 dB, averaging over the entire dataset. Defibtech’s rhythm analysis algorithm was applied to the filtered data. We found a sensitivity improvement from 67.7 to 91.3% and 62.7 to 78% for VF and rapid VT, respectively, and specificity improved from 96.2 to 96.5% and 91.5 to 92.7% for normal sinus rhythm (NSR) and other non-shockables, respectively.

High accuracy distinction of shockable and non-shockable arrhythmias in abnormal classes through wavelet transform with pseudo differential like operators

“…The accuracy is slightly high for the existing method since the evaluation was performed on around five hundred samples where non-shockable samples (e.g., NSR samples) numbers are relatively higher than the shockable samples. In addition, we observe from Table 8 the methods as 12 , 30 – 35 , and 36 achieved the high-performance results for shockable versus non-shockable arrhythmia distinction, but PEA arrhythmia is not individually considered there. As has been explained in the introduction the discrimination of PEA arrhythmia is particularly important in the abnormal classes regarding the actual application of AED.…”

Deep Learning Strategy for Sliding ECG Analysis during Cardiopulmonary Resuscitation: Influence of the Hands-Off Time on Accuracy

“…The ECG analysis concept in this study brings a new perspective to the state of the art. The algorithm monitors the rhythm during continuous CPR, not limited to analysis only during CC [14,16,17,20,22,24,25,27,[29][30][31][35][36][37]51,52] or only during clean ECG [17,31,39,41,49,53,54], as summarized in Figure 10. Although most published algorithms have been optimized and report the performance for either CPR-ECG or fully Clean-ECG signal parts during OHCA, the shock advisory performance of our algorithm CNN-CPR (10 s) is in the high range for both signal parts: CPR-ECG (Se = 92-94.4%, Sp = 92.2-99.5%) for decision time in the range [−15; 0 s]; fully Clean-ECG (Se = 98.7%, Sp = 98.9-100%) for decision time equal to 10 s. The difficult task for CPR-ECG analysis was managed here without additional processing (ECG prefiltering, and additional sensors), which can be found in some studies [14,16,17,20,36,37,51].…”

“…Several approaches seeking a simpler AED implementation use only one ECG input, where periodic CC artefacts are suppressed by pattern matching algorithms [22], coherent line removal [23], and Kalman filters [24]. Short-time Fourier transform images of the ECG spectrum have been shown to be effective for filtering out CC artefacts while processed by a condition-based filtering algorithm [25] and deep convolutional encoder/decoder [26]. Whether with or without reference signals, the aforementioned methods have common disabilities in providing filtered ECG signals either with insufficiently suppressed CC artefact components or distorted ECG waves.…”

“…Whether with or without reference signals, the aforementioned methods have common disabilities in providing filtered ECG signals either with insufficiently suppressed CC artefact components or distorted ECG waves. These warped ECG signals limit the accuracy of the automated shock advisory algorithms whether they are conventionally trained for ECG signals without artefacts [13,[15][16][17]19,20,25,26] or apply specially optimized decision rules for detection of ventricular fibrillation during CPR [22,27].…”

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

“…To perform reliable and accurate ECG waveform analysis without interrupting CPR, a number of signal processing solutions have been proposed to remove CC artifacts in the past two decades ( Gong et al, 2013 ). One solution is to suppress artifacts using only the ECG waveform, such as the Kalman filter ( Ruiz de Gauna et al, 2008 ), independent component analysis ( Granegger et al, 2011 ), coherent line removal algorithm ( Amann et al, 2010 ), empirical mode decomposition ( Lo et al, 2013 ) and condition-based filtering algorithm ( Hajeb-Mohammadalipour et al, 2021 ). Although artifacts can be strongly suppressed, and the signal-to-noise ratio (SNR) is markedly improved, the specificity for VF detection is insignificantly improved using these methods.…”