Application of Convolutional Neural Network for Decoding of 12-Lead Electrocardiogram from a Frequency-Modulated Audio Stream (Sonified ECG).

Research of novel biosignal modalities with application to remote patient monitoring is a subject of state-of-the-art developments. This study is focused on sonified ECG modality, which can be transmitted as an acoustic wave and received by GSM (Global System for Mobile Communications) microphones. Thus, the wireless connection between the patient module and the cloud server can be provided over an audio channel, such as a standard telephone call or audio message. Patients, especially the elderly or visually impaired, can benefit from ECG sonification because the wireless interface is readily available, facilitating the communication and transmission of secure ECG data from the patient monitoring device to the remote server. The aim of this study is to develop an AI-driven algorithm for 12-lead ECG sonification to support diagnostic reliability in the signal processing chain of the audio ECG stream. Our methods present the design of two algorithms: (1) a transformer (ECG-to-Audio) based on the frequency modulation (FM) of eight independent ECG leads in the very low frequency band (300-2700 Hz); and (2) a transformer (Audio-to-ECG) based on a four-layer 1D convolutional neural network (CNN) to decode the audio ECG stream (10 s @ 11 kHz) to the original eight-lead ECG (10 s @ 250 Hz). The CNN model is trained in unsupervised regression mode, searching for the minimum error between the transformed and original ECG signals. The results are reported using the PTB-XL 12-lead ECG database (21,837 recordings), split 50:50 for training and test. The quality of FM-modulated ECG audio is monitored by short-time Fourier transform, and examples are illustrated in this paper and supplementary audio files. The errors of the reconstructed ECG are estimated by a popular ECG diagnostic toolbox. They are substantially low in all ECG leads: amplitude error (quartile range RMSE = 3-7 µV, PRD = 2-5.2%), QRS detector (Se, PPV > 99.7%), P-QRS-T fiducial points' time deviation (<2 ms). Low errors generalized across diverse patients and arrhythmias are a testament to the efficacy of the developments. They support 12-lead ECG sonification as a wireless interface to provide reliable data for diagnostic measurements by automated tools or medical experts.

Delineation of 12-Lead ECG Representative Beats Using Convolutional Encoder-Decoders with Residual and Recurrent Connections.

The aim of this study is to address the challenge of 12-lead ECG delineation by different encoder-decoder architectures of deep neural networks (DNNs). This study compares four concepts for encoder-decoders based on a fully convolutional architecture (CED-Net) and its modifications with a recurrent layer (CED-LSTM-Net), residual connections between symmetrical encoder and decoder feature maps (CED-U-Net), and sequential residual blocks (CED-Res-Net). All DNNs transform 12-lead representative beats to three diagnostic ECG intervals (P-wave, QRS-complex, QT-interval) used for the global delineation of the representative beat (P-onset, P-offset, QRS-onset, QRS-offset, T-offset). All DNNs were trained and optimized using the large PhysioNet ECG database (PTB-XL) under identical conditions, applying an advanced approach for machine-based supervised learning with a reference algorithm for ECG delineation (ETM, Schiller AG, Baar, Switzerland). The test results indicate that all DNN architectures are equally capable of reproducing the reference delineation algorithm's measurements in the diagnostic PTB database with an average P-wave detection accuracy (96.6%) and time and duration errors: mean values (-2.6 to 2.4 ms) and standard deviations (2.9 to 11.4 ms). The validation according to the standard-based evaluation practices of diagnostic electrocardiographs with the CSE database outlines a CED-Net model, which measures P-duration (2.6 ± 11.0 ms), PQ-interval (0.9 ± 5.8 ms), QRS-duration (-2.4 ± 5.4 ms), and QT-interval (-0.7 ± 10.3 ms), which meet all standard tolerances. Noise tests with high-frequency, low-frequency, and power-line frequency noise (50/60 Hz) confirm that CED-Net, CED-Res-Net, and CED-LSTM-Net are robust to all types of noise, mostly presenting a mean duration error < 2.5 ms when compared to measurements without noise. Reduced noise immunity is observed for the U-net architecture. Comparative analysis with other published studies scores this research within the lower range of time errors, highlighting its competitive performance.

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

This study aims to present a novel deep learning algorithm for a sliding shock advisory decision during cardiopulmonary resuscitation (CPR) and its performance evaluation as a function of the cumulative hands-off time. We retrospectively used 13,570 CPR episodes from out-of-hospital cardiac arrest (OHCA) interventions reviewed in a period of interest from 30 s before to 10 s after regular analysis of automated external defibrillators (AEDs). Three convolutional neural networks (CNNs) with raw ECG input (duration of 5, 10, and 15 s) were applied for the shock advisory decision during CPR in 26 sequential analyses shifted by 1 s. The start and stop of chest compressions (CC) can occur at arbitrary times in sequential slides; therefore, the sliding hands-off time (sHOT) quantifies the cumulative CC-free portion of the analyzed ECG. An independent test with CPR episodes in 393 ventricular fibrillations (VF), 177 normal sinus rhythms (NSR), 1848 other non-shockable rhythms (ONR), and 3979 asystoles (ASYS) showed a substantial improvement of VF sensitivity when increasing the analysis duration from 5 s to 10 s. Specificity was not dependent on the ECG analysis duration. The 10 s CNN model presented the best performance: 92-94.4% (VF), 92.2-94% (ASYS), 96-97% (ONR), and 98.2-99.5% (NSR) for sliding decision times during CPR; 98-99% (VF), 98.2-99.8% (ASYS), 98.8-99.1 (ONR), and 100% (NSR) for sliding decision times after end of CPR. We identified the importance of sHOT as a reliable predictor of performance, accounting for the minimal sHOT interval of 2-3 s that provides a reliable rhythm detection satisfying the American Heart Association (AHA) standards for AED rhythm analysis. The presented technology for sliding shock advisory decision during CPR achieved substantial performance improvement in short hands-off periods (>2 s), such as insufflations or pre-shock pauses. The performance was competitive despite 1-2.8% point lower ASYS detection during CPR than the standard requirement (95%) for non-noisy ECG signals. The presented deep learning strategy is a basis for improved CPR practices involving both continuous CC and CC with insufflations, associated with minimal CC interruptions for reconfirmation of non-shockable rhythms (minimum hands-off time) and early treatment of VF (minimal pre-shock pauses).

Effect of synchronization of firings of different motor unit types on the force variability in a model of the rat medial gastrocnemius muscle.

The synchronized firings of active motor units (MUs) increase the oscillations of muscle force, observed as physiological tremor. This study aimed to investigate the effects of synchronizing the firings within three types of MUs (slow-S, fast resistant to fatigue-FR, and fast fatigable-FF) on the muscle force production using a mathematical model of the rat medial gastrocnemius muscle. The model was designed based on the actual proportion and physiological properties of MUs and motoneurons innervating the muscle. The isometric muscle and MU forces were simulated by a model predicting non-synchronized firing of a pool of 57 MUs (including 8 S, 23 FR, and 26 FF) to ascertain a maximum excitatory signal when all MUs were recruited into the contraction. The mean firing frequency of each MU depended upon the twitch contraction time, whereas the recruitment order was determined according to increasing forces (the size principle). The synchronization of firings of individual MUs was simulated using four different modes and inducing the synchronization of firings within three time windows (± 2, ± 4, and ± 6 ms) for four different combinations of MUs. The synchronization was estimated using two parameters, the correlation coefficient and the cross-interval synchronization index. The four scenarios of synchronization increased the values of the root-mean-square, range, and maximum force in correlation with the increase of the time window. Greater synchronization index values resulted in higher root-mean-square, range, and maximum of force outcomes for all MU types as well as for the whole muscle output; however, the mean spectral frequency of the forces decreased, whereas the mean force remained nearly unchanged. The range of variability and the root-mean-square of forces were higher for fast MUs than for slow MUs; meanwhile, the relative values of these parameters were highest for slow MUs, indicating their important contribution to muscle tremor, especially during weak contractions.

Atrioventricular Synchronization for Detection of Atrial Fibrillation and Flutter in One to Twelve ECG Leads Using a Dense Neural Network Classifier.

This study investigates the use of atrioventricular (AV) synchronization as an important diagnostic criterion for atrial fibrillation and flutter (AF) using one to twelve ECG leads. Heart rate, lead-specific AV conduction time, and P-/f-wave amplitude were evaluated by three representative ECG metrics (mean value, standard deviation), namely RR-interval (RRi-mean, RRi-std), PQ-interval (PQi-mean, PQI-std), and PQ-amplitude (PQa-mean, PQa-std), in 71,545 standard 12-lead ECG records from the six largest PhysioNet CinC Challenge 2021 databases. Two rhythm classes were considered (AF, non-AF), randomly assigning records into training (70%), validation (20%), and test (10%) datasets. In a grid search of 19, 55, and 83 dense neural network (DenseNet) architectures and five independent training runs, we optimized models for one-lead, six-lead (chest or limb), and twelve-lead input features. Lead-set performance and SHapley Additive exPlanations (SHAP) input feature importance were evaluated on the test set. Optimal DenseNet architectures with the number of neurons in sequential [1st, 2nd, 3rd] hidden layers were assessed for sensitivity and specificity: DenseNet [16,16,0] with primary leads (I or II) had 87.9-88.3 and 90.5-91.5%; DenseNet [32,32,32] with six limb leads had 90.7 and 94.2%; DenseNet [32,32,4] with six chest leads had 92.1 and 93.2%; and DenseNet [128,8,8] with all 12 leads had 91.8 and 95.8%, indicating sensitivity and specificity values, respectively. Mean SHAP values on the entire test set highlighted the importance of RRi-mean (100%), RR-std (84%), and atrial synchronization (40-60%) for the PQa-mean (aVR, I), PQi-std (V2, aVF, II), and PQi-mean (aVL, aVR). Our focus on finding the strongest AV synchronization predictors of AF in 12-lead ECGs would lead to a comprehensive understanding of the decision-making process in advanced neural network classifiers. DenseNet self-learned to rely on a few ECG behavioral characteristics: first, characteristics usually associated with AF conduction such as rapid heart rate, enhanced heart rate variability, and large PQ-interval deviation in V2 and inferior leads (aVF, II); second, characteristics related to a typical P-wave pattern in sinus rhythm, which is best distinguished from AF by the earliest negative P-peak deflection of the right atrium in the lead (aVR) and late positive left atrial deflection in lateral leads (I, aVL). Our results on lead-selection and feature-selection practices for AF detection should be considered for one- to twelve-lead ECG signal processing settings, particularly those measuring heart rate, AV conduction times, and P-/f-wave amplitudes. Performances are limited to the AF diagnostic potential of these three metrics. SHAP value importance can be used in combination with a human expert's ECG interpretation to change the focus from a broad observation of 12-lead ECG morphology to focusing on the few AV synchronization findings strongly predictive of AF or non-AF arrhythmias. Our results are representative of AV synchronization findings across a broad taxonomy of cardiac arrhythmias in large 12-lead ECG databases.

Optimization of End-to-End Convolutional Neural Networks for Analysis of Out-of-Hospital Cardiac Arrest Rhythms during Cardiopulmonary Resuscitation.

High performance of the shock advisory analysis of the electrocardiogram (ECG) during cardiopulmonary resuscitation (CPR) in out-of-hospital cardiac arrest (OHCA) is important for better management of the resuscitation protocol. It should provide fewer interruptions of chest compressions (CC) for non-shockable organized rhythms (OR) and Asystole, or prompt CC stopping for early treatment of shockable ventricular fibrillation (VF). Major disturbing factors are strong CC artifacts corrupting raw ECG, which we aimed to analyze with optimized end-to-end convolutional neural network (CNN) without pre-filtering or additional sensors. The hyperparameter random search of 1500 CNN models with 2-7 convolutional layers, 5-50 filters and 5-100 kernel sizes was done on large databases from independent OHCA interventions for training (3001 samples) and validation (2528 samples). The best model, named CNN3-CC-ECG network with three convolutional layers (filters@kernels: 5@5,25@20,50@20) presented Sensitivity Se(VF) = 89%(268/301), Specificity Sp(OR) = 91.7%(1504/1640), Sp(Asystole) = 91.1%(3325/3650) on an independent test OHCA database. CNN3-CC-ECG's ability to effectively extract features from raw ECG signals during CPR was comprehensively demonstrated, and the dependency on the CPR corruption level in ECG was tested. We denoted a significant drop of Se(VF) = 74.2% and Sp(OR) = 84.6% in very strong CPR artifacts with a signal-to-noise ratio of SNR < -9 dB, p < 0.05. Otherwise, for strong, moderate and weak CC artifacts (SNR > -9 dB, -6 dB, -3 dB), we observed insignificant performance differences: Se(VF) = 92.5-96.3%, Sp(OR) = 93.4-95.5%, Sp(Asystole) = 92.6-94.0%, p > 0.05. Performance stability with respect to CC rate was validated. Generalizable application of the optimized computationally efficient CNN model was justified by an independent OHCA database, which to our knowledge is the largest test dataset with real-life cardiac arrest rhythms during CPR.

Application of Dense Neural Networks for Detection of Atrial Fibrillation and Ranking of Augmented ECG Feature Set.

Considering the significant burden to patients and healthcare systems globally related to atrial fibrillation (AF) complications, the early AF diagnosis is of crucial importance. In the view of prominent perspectives for fast and accurate point-of-care arrhythmia detection, our study optimizes an artificial neural network (NN) classifier and ranks the importance of enhanced 137 diagnostic ECG features computed from time and frequency ECG signal representations of short single-lead strips available in 2017 Physionet/CinC Challenge database. Based on hyperparameters' grid search of densely connected NN layers, we derive the optimal topology with three layers and 128, 32, 4 neurons per layer (DenseNet-3@128-32-4), which presents maximal F1-scores for classification of Normal rhythms (0.883, 5076 strips), AF (0.825, 758 strips), Other rhythms (0.705, 2415 strips), Noise (0.618, 279 strips) and total F1 relevant to the CinC Challenge of 0.804, derived by five-fold cross-validation. DenseNet-3@128-32-4 performs equally well with 137 to 32 features and presents tolerable reduction by about 0.03 to 0.06 points for limited input sets, including 8 and 16 features, respectively. The feature reduction is linked to effective application of a comprehensive method for computation of the feature map importance based on the weights of the activated neurons through the total path from input to specific output in DenseNet. The detailed analysis of 20 top-ranked ECG features with greatest importance to the detection of each rhythm and overall of all rhythms reveals DenseNet decision-making process, noticeably corresponding to the cardiologists' diagnostic point of view.

Fully Convolutional Deep Neural Networks with Optimized Hyperparameters for Detection of Shockable and Non-Shockable Rhythms.

Deep neural networks (DNN) are state-of-the-art machine learning algorithms that can be learned to self-extract significant features of the electrocardiogram (ECG) and can generally provide high-output diagnostic accuracy if subjected to robust training and optimization on large datasets at high computational cost. So far, limited research and optimization of DNNs in shock advisory systems is found on large ECG arrhythmia databases from out-of-hospital cardiac arrests (OHCA). The objective of this study is to optimize the hyperparameters (HPs) of deep convolutional neural networks (CNN) for detection of shockable (Sh) and nonshockable (NSh) rhythms, and to validate the best HP settings for short and long analysis durations (2-10 s). Large numbers of (Sh + NSh) ECG samples were used for training (720 + 3170) and validation (739 + 5921) from Holters and defibrillators in OHCA. An end-to-end deep CNN architecture was implemented with one-lead raw ECG input layer (5 s, 125 Hz, 2.5 uV/LSB), configurable number of 5 to 23 hidden layers and output layer with diagnostic probability p ∈ [0: Sh,1: NSh]. The hidden layers contain N convolutional blocks × 3 layers (Conv1D (filters = Fi, kernel size = Ki), max-pooling (pool size = 2), dropout (rate = 0.3)), one global max-pooling and one dense layer. Random search optimization of HPs = {N, Fi, Ki}, i = 1, … N in a large grid of N = [1, 2, … 7], Fi = [5;50], Ki = [5;100] was performed. During training, the model with maximal balanced accuracy BAC = (Sensitivity + Specificity)/2 over 400 epochs was stored. The optimization principle is based on finding the common HPs space of a few top-ranked models and prediction of a robust HP setting by their median value. The optimal models for 1-7 CNN layers were trained with different learning rates LR = [10-5; 10-2] and the best model was finally validated on 2-10 s analysis durations. A number of 4216 random search models were trained. The optimal models with more than three convolutional layers did not exhibit substantial differences in performance BAC = (99.31-99.5%). Among them, the best model was found with {N = 5, Fi = {20, 15, 15, 10, 5}, Ki = {10, 10, 10, 10, 10}, 7521 trainable parameters} with maximal validation performance for 5-s analysis (BAC = 99.5%, Se = 99.6%, Sp = 99.4%) and tolerable drop in performance (<2% points) for very short 2-s analysis (BAC = 98.2%, Se = 97.6%, Sp = 98.7%). DNN application in future-generation shock advisory systems can improve the detection performance of Sh and NSh rhythms and can considerably shorten the analysis duration complying with resuscitation guidelines for minimal hands-off pauses.

Simulating Arbitrary Electrode Reversals in Standard 12-lead ECG.

Electrode reversal errors in standard 12-lead electrocardiograms (ECG) can produce significant ECG changes and, in turn, misleading diagnoses. Their detection is important but mostly limited to the design of criteria using ECG databases with simulated reversals, without Wilson's central terminal (WCT) potential change. This is, to the best of our knowledge, the first study that presents an algebraic transformation for simulation of all possible ECG cable reversals, including those with displaced WCT, where most of the leads appear with distorted morphology. The simulation model of ECG electrode swaps and the resultant WCT potential change is derived in the standard 12-lead ECG setup. The transformation formulas are theoretically compared to known limb lead reversals and experimentally proven for unknown limb-chest electrode swaps using a 12-lead ECG database from 25 healthy volunteers (recordings without electrode swaps and with 5 unicolor pairs swaps, including red (right arm-C1), yellow (left arm-C2), green (left leg (LL) -C3), black (right leg (RL)-C5), all unicolor pairs). Two applications of the transformation are shown to be feasible: 'Forward' (simulation of reordered leads from correct leads) and 'Inverse' (reconstruction of correct leads from an ECG recorded with known electrode reversals). Deficiencies are found only when the ground RL electrode is swapped as this case requires guessing the unknown RL electrode potential. We suggest assuming that potential to be equal to that of the LL electrode. The 'Forward' transformation is important for comprehensive training platforms of humans and machines to reliably recognize simulated electrode swaps using the available resources of correctly recorded ECG databases. The 'Inverse' transformation can save time and costs for repeated ECG recordings by reconstructing the correct lead set if a lead swap is detected after the end of the recording. In cases when the electrode reversal is unknown but a prior correct ECG recording of the same patient is available, the 'Inverse' transformation is tested to detect the exact swapping of the electrodes with an accuracy of (96% to 100%).

Human Identification by Cross-Correlation and Pattern Matching of Personalized Heartbeat: Influence of ECG Leads and Reference Database Size.

Human identification (ID) is a biometric task, comparing single input sample to many stored templates to identify an individual in a reference database. This paper aims to present the perspectives of personalized heartbeat pattern for reliable ECG-based identification. The investigations are using a database with 460 pairs of 12-lead resting electrocardiograms (ECG) with 10-s durations recorded at time-instants T1 and T2 > T1 + 1 year. Intra-subject long-term ECG stability and inter-subject variability of personalized PQRST (500 ms) and QRS (100 ms) patterns is quantified via cross-correlation, amplitude ratio and pattern matching between T1 and T2 using 7 features × 12-leads. Single and multi-lead ID models are trained on the first 230 ECG pairs. Their validation on 10, 20, ... 230 reference subjects (RS) from the remaining 230 ECG pairs shows: (i) two best single-lead ID models using lead II for a small population RS = (10-140) with identification accuracy AccID = (89.4-67.2)% and aVF for a large population RS = (140-230) with AccID = (67.2-63.9)%; (ii) better performance of the 6-lead limb vs. the 6-lead chest ID model-(91.4-76.1)% vs. (90.9-70)% for RS = (10-230); (iii) best performance of the 12-lead ID model-(98.4-87.4)% for RS = (10-230). The tolerable reference database size, keeping AccID > 80%, is RS = 30 in the single-lead ID scenario (II); RS = 50 (6 chest leads); RS = 100 (6 limb leads), RS > 230-maximal population in this study (12-lead ECG).

Biometric verification by cross-correlation analysis of 12-lead ECG patterns: Ranking of the most reliable peripheral and chest leads.

BACKGROUND: Electrocardiogram (ECG)-based biometrics relies on the most stable and unique beat patterns, i.e. those with maximal intra-subject and minimal inter-subject waveform differences seen from different leads. We investigated methodology to evaluate those differences, aiming to rank the most prominent single and multi-lead ECG sets for biometric verification across a large population. METHODS: A clinical standard 12-lead resting ECG database, including 460 pairs of remote recordings (distanced 1year apart) was used. Inter-subject beat waveform differences were studied by cross-correlation and amplitude relations of average PQRST (500ms) and QRS (100ms) patterns, using 8 features/lead in 12-leads. Biometric verification models based on stepwise linear discriminant classifier were trained on the first half of records. True verification rate (TVR) on the remaining test data was further reported as a common mean of the correctly verified equal subjects (true acceptance rate) and correctly rejected different subjects (true rejection rate). RESULTS AND CONCLUSIONS: In single-lead ECG human identity applications, we found maximal TVR (87-89%) for the frontal plane leads (I, -aVR, II) within (0-60°) sector. Other leads were ranked: inferior (85%), lateral to septal (82-81%), with intermittent V3 drop (77.6%), suggesting anatomical landmark displacements. ECG pattern view from multi-lead sets improved TVR: chest (91.3%), limb (94.6%), 12-leads (96.3%).

Intersubject variability and intrasubject reproducibility of 12-lead ECG metrics: Implications for human verification.

BACKGROUND: Electrocardiogram (ECG) biometrics is an advanced technology, not yet covered by guidelines on criteria, features and leads for maximal authentication accuracy. OBJECTIVE: This study aims to define the minimal set of morphological metrics in 12-lead ECG by optimization towards high reliability and security, and validation in a person verification model across a large population. METHODS: A standard 12-lead resting ECG database from 574 non-cardiac patients with two remote recordings (>1year apart) was used. A commercial ECG analysis module (Schiller AG) measured 202 morphological features, including lead-specific amplitudes, durations, ST-metrics, and axes. Coefficient of variation (CV, intersubject variability) and percent-mean-absolute-difference (PMAD, intrasubject reproducibility) defined the optimization (PMAD/CV→min) and restriction (CV<30%) criteria for selection of the most stable and distinctive features. Linear discriminant analysis (LDA) validated the non-redundant feature set for person verification. RESULTS AND CONCLUSIONS: Maximal LDA verification sensitivity (85.3%) and specificity (86.4%) were validated for 11 optimal features: R-amplitude (I,II,V1,V2,V3,V5), S-amplitude (V1,V2), Tnegative-amplitude (aVR), and R-duration (aVF,V1).

Recognition of Supraventricular Arrhythmias in Holter ECG Recordings by ECHOView Color Map: A Case Series Study.

Ambulatory 24-72 h Holter ECG monitoring is recommended for patients with suspected arrhythmias, which are often transitory and might remain unseen in resting standard 12-lead ECG. Holter manufacturers provide software diagnostic tools to assist clinicians in evaluating these large amounts of data. Nevertheless, the identification of short arrhythmia events and differentiation of the arrhythmia type might be a problem in limited Holter ECG leads. This observational clinical study aims to explore a novel and weakly investigated ECG modality integrated into a commercial diagnostic tool ECHOView (medilog DARWIN 2, Schiller AG, Switzerland), while used for the interpretation of long-term Holter-ECG records by a cardiologist. The ECHOView transformation maps the beat waveform amplitude to a color-coded bar. One ECHOView page integrates stacked color bars of about 1740 sequential beats aligned by R-peak in a window (R ± 750 ms). The collected 3-lead Holter ECG recordings from 86 patients had a valid duration of 21 h 20 min (19 h 30 min-22 h 45 min), median (quartile range). The ECG rhythm was reviewed with 3491 (3192-3723) standard-grid ECG pages and a substantially few number of 51 (44-59) ECHOView pages that validated the ECHOView compression ratio of 67 (59-74) times. Comments on the ECG rhythm and ECHOView characteristic patterns are provided for 14 examples representative of the most common rhythm disorders seen in our population, including supraventricular arrhythmias (supraventricular extrasystoles, paroxysmal supraventricular arrhythmia, sinus tachycardia, supraventricular tachycardia, atrial fibrillation, and flutter) and ventricular arrhythmias (ventricular extrasystoles, non-sustained ventricular tachycardia). In summary, the ECHOView color map transforms the ECG modality into a novel diagnostic image of the patient's rhythm that is comprehensively interpreted by a cardiologist. ECHOView has the potential to facilitate the manual overview of Holter ECG recordings, to visually identify short-term arrhythmia episodes, and to refine the diagnosis, especially in high-rate arrhythmias.

A Randomized Comparison of Delivered Energy in Cardioversion of Atrial Fibrillation: Biphasic Truncated Exponential Versus Pulsed Biphasic Waveforms.

A few randomized trials have compared impedance-compensated biphasic defibrillators in clinical use. We aim to compare pulsed biphasic (PB) and biphasic truncated exponential (BTE) waveforms in a non-inferiority cardioversion (CVS) study. This was a prospective monocentric randomized clinical trial. Eligible patients admitted for elective CVS of atrial fibrillation (AF) between February 2019 and March 2020 were alternately randomized to treatment with either a PB defibrillator (DEFIGARD TOUCH7, Schiller Médical, Wissembourg, France) or a BTE high-energy (BTE-HE) defibrillator (LIFEPAK15, Physio-Control Inc., Redmond, WA, USA). Fixed-energy protocol (200-200-200 J) was administered. CVS success was accepted if sinus rhythm was restored at 1 min post-shock. The study design considered non-inferiority testing of the primary outcome: cumulative delivered energy (CDE). Seventy-three out of 78 randomized patients received allocated intervention: 38 BTE-HE (52%), 35 PB (48%). Baseline characteristics were well-balanced between groups (p > 0.05). Both waveforms had similar CDE (mean ± standard deviation, 95% confidence interval): BTE-HE (253.9 ± 120.2 J, 214-293 J) vs. PB (226.0 ± 109.8 J, 188-264 J), p = 0.31. Indeed, effective PB shocks delivered significantly lower energies by mean of 25.6 J (95% CI 24-27.1 J, p < 0.001). Success rates were similar (BTE-HE vs. PB): 1 min first-shock (84.2% vs. 82.9%), 1 min CVS (97.4% vs. 94.3%), 2 h CVS (94.7% vs. 94.3%), 24 h CVS (92.1% vs. 94.3%), p > 0.05. Safety analysis did not find CVS hazards, reporting insignificant changes of myocardial-specific biomarkers, transient and rare ST-segment deviations, and no case of harmful tachyarrhythmias and apnea. Cardioversion of AF with fixed-energy protocol 200-200-200 J was highly efficient and safe for both PB and BTE-HE waveforms. These similar performances were achieved despite differences in the waveforms' technical design, associated with significantly lower delivered energy for the effective PB shocks. Clinical Trial Registration: Registration number: NCT04032678, trial register: ClinicalTrials.gov.

Analyze Whilst Compressing algorithm for detection of ventricular fibrillation during CPR: A comparative performance evaluation for automated external defibrillators.

OBJECTIVE: The aim of this study was to present new combination of algorithms for rhythm analysis during cardiopulmonary resuscitation (CPR) in automated external defibrillators (AED), called Analyze Whilst Compressing (AWC), designed for decreasing pre-shock pause and early stopping of chest compressions (CC) for treating refibrillation. METHODS: Two stages for AED rhythm analysis were presented, namely, "Standard Analysis Stage" (conventional shock-advisory analysis run over 5 s after CC interruption every two minutes) and "AWC Stage" (two-step sequential analysis process during CPR). AWC steps were run in presence of CC (Step1), and if shockable rhythm was detected then a reconfirmation step was run in absence of CC (Step2, analysis duration 5 s). RESULTS: In total 16,057 ECG strips from 2916 out-of-hospital cardiac arrest (OHCA) patients treated with AEDs (DEFIGARD TOUCH7, Schiller Médical, France) were subjected patient-wise to AWC training (8559 strips, 1604 patients) and validation (7498 strips, 1312 patients). Considering validation results, "Standard Analysis Stage" presented ventricular fibrillation (VF) sensitivity Se = 98.3% and non-shockable rhythm specificity Sp>99%; "AWC Stage" decision after Step2 reconfirmation achieved Se = 92.1%, Sp>99%. CONCLUSION: AWC presented similar performances to other AED algorithms during CPR, fulfilling performance goals recommended by standards. AWC provided advances in the challenge for improving CPR quality by: (i) not interrupting chest compressions for prevalent part of non-shockable rhythms (66-83%); (ii) minimizing pre-shock pause for 92.1% of VF patients. AWC required hands-off reconfirmation in 34.4% of cases. Reconfirmation was also common limitation of other reported algorithms (25.7-100%) although following different protocols for triggering chest compression resumption and shock delivery.

Bench study of the accuracy of a commercial AED arrhythmia analysis algorithm in the presence of electromagnetic interferences.

This paper presents a bench study on a commercial automated external defibrillator (AED). The objective was to evaluate the performance of the defibrillation advisory system and its robustness against electromagnetic interferences (EMI) with central frequencies of 16.7, 50 and 60 Hz. The shock advisory system uses two 50 and 60 Hz band-pass filters, an adaptive filter to identify and suppress 16.7 Hz interference, and a software technique for arrhythmia analysis based on morphology and frequency ECG parameters. The testing process includes noise-free ECG strips from the internationally recognized MIT-VFDB ECG database that were superimposed with simulated EMI artifacts and supplied to the shock advisory system embedded in a real AED. Measurements under special consideration of the allowed variation of EMI frequency (15.7-17.4, 47-52, 58-62 Hz) and amplitude (1 and 8 mV) were performed to optimize external validity. The accuracy was reported using the American Heart Association (AHA) recommendations for arrhythmia analysis performance. In the case of artifact-free signals, the AHA performance goals were exceeded for both sensitivity and specificity: 99% for ventricular fibrillation (VF), 98% for rapid ventricular tachycardia (VT), 90% for slow VT, 100% for normal sinus rhythm, 100% for asystole and 99% for other non-shockable rhythms. In the presence of EMI, the specificity for some non-shockable rhythms (NSR, N) may be affected in some specific cases of a low signal-to-noise ratio and extreme frequencies, leading to a drop in the specificity with no more than 7% point. The specificity for asystole and the sensitivity for VF and rapid VT in the presence of any kind of 16.7, 50 or 60 Hz EMI simulated artifact were shown to reach the equivalence of sensitivity required for non-noisy signals. In conclusion, we proved that the shock advisory system working in a real AED operates accurately according to the AHA recommendations without artifacts and in the presence of EMI. The results may be affected for specificity in the case of a low signal-to-noise ratio or in some extreme frequency setting.

Cardioversion of Atrial Fibrillation and Flutter: Comparative Study of Pulsed vs. Low Energy Biphasic Truncated Exponential Waveforms.

BACKGROUND: Despite the widespread use of biphasic waveforms for cardioversion and defibrillation, the efficacy and safety of shocks has only been compared in a few studies. METHODS: This retrospective study aims at comparing the efficacy and safety of biphasic truncated exponential (BTE) pulsed energy (PE) waveform with a BTE low energy (LE) waveform for cardioversion of atrial fibrillation (AF) and atrial flutter (AFL). The treatment energies were following an escalating protocol for PE waveform (120-200-200J in AF and 30-120-200J in AFL) and LE waveform (100-200-200J in AF and 30-100-200J in AFL). The protocol was stopped at successful cardioversion (sinus rhythm at 1 minute post-shock), otherwise after the 3rd shock. If the 3rd BTE shock failed, a monophasic shock of 360J was delivered. RESULTS: From May 2008 to November 2017, 193 patients (153 PE, 40 LE) were included in the study. Both groups significantly differed in a few characteristics, including chest circumference (p<0.05). After adjustment, the success rate was not significantly different for the two waveforms (94.5% PE vs 92.5% LE, Odds Ratio [95% Confidence Interval] = 0.25 [0.03-2.2]).There was no difference in safety: post-shock changes in Hsc-TnI levels were similar (p=0.25). The efficient cumulative energy was particularly related with BSA (ß = 131.5, p=0.05), AF/AFL duration (ß = 0.24, p=0.01) and gender (ß = 61.8, p=0.05). CONCLUSIONS: The major clinical implications of this study concern the high success rate of cardioversion with both biphasic pulses and no superiority of LE over PE waveform with an excellent safety profile without post-shock myocardial injuries.

Perspectives of human verification via binary QRS template matching of single-lead and 12-lead electrocardiogram.

OBJECTIVE: This study aims to validate the 12-lead electrocardiogram (ECG) as a biometric modality based on two straightforward binary QRS template matching characteristics. Different perspectives of the human verification problem are considered, regarding the optimal lead selection and stability over sample size, gender, age, heart rate (HR). METHODS: A clinical 12-lead resting ECG database, including a population of 460 subjects with two-session recordings (>1 year apart) is used. Cost-effective strategies for extraction of personalized QRS patterns (100ms) and binary template matching estimate similarity in the time scale (matching time) and dissimilarity in the amplitude scale (mismatch area). The two-class person verification task, taking the decision to validate or to reject the subject identity is managed by linear discriminant analysis (LDA). Non-redundant LDA models for different lead configurations (I,II,III,aVF,aVL,aVF,V1-V6) are trained on the first half of 230 subjects by stepwise feature selection until maximization of the area under the receiver operating characteristic curve (ROC AUC). The operating point on the training ROC at equal error rate (EER) is tested on the independent dataset (second half of 230 subjects) to report unbiased validation of test-ROC AUC and true verification rate (TVR = 100-EER). The test results are further evaluated in groups by sample size, gender, age, HR. RESULTS AND DISCUSSION: The optimal QRS pattern projection for single-lead ECG biometric modality is found in the frontal plane sector (60°-0°) with best (Test-AUC/TVR) for lead II (0.941/86.8%) and slight accuracy drop for -aVR (-0.017/-1.4%), I (-0.01/-1.5%). Chest ECG leads have degrading accuracy from V1 (0.885/80.6%) to V6 (0.799/71.8%). The multi-lead ECG improves verification: 6-chest (0.97/90.9%), 6-limb (0.986/94.3%), 12-leads (0.995/97.5%). The QRS pattern matching model shows stable performance for verification of 10 to 230 individuals; insignificant degradation of TVR in women by (1.2-3.6%), adults ≥70 years (3.7%), younger <40 years (1.9%), HR<60bpm (1.2%), HR>90bpm (3.9%), no degradation for HR change (0 to >20bpm).

Ranking of the most reliable beat morphology and heart rate variability features for the detection of atrial fibrillation in short single-lead ECG.

OBJECTIVE: This study participated in the 2017 PhysioNet/CinC Challenge dedicated to the classification of atrial fibrillation (AF), normal sinus rhythm (Normal), other arrhythmia (Other) and strong noise, using single-lead electrocardiogram (ECG) recordings with a duration <60 s. The aim is to apply a linear threshold-based strategy for arrhythmia classification, ranking the most powerful time domain ECG features that could be easily reproduced on any platform. APPROACH: An algorithm for time domain ECG analysis was designed to extract 44 features with focus on the following: noise detection; heart rate variability (HRV) analysis; beat morphology analysis and delineation of P-, QRS-, and T-waves in the robust average beat; detection of atrial activity by the presence of P-waves in the average beat and atrial fibrillatory waves (f-waves) during TQ intervals. A linear discriminant analysis (LDA) classifier was optimized on the Challenge training set (8528 ECGs) by stepwise selection of a nonredundant feature set until maximization of the Challenge F1 score. Heart rate (HR) was an independent factor for the LDA classifier design, particular to bradycardia (HR ⩽ 50 bpm), normal rhythm (HR = 50-100 bpm), tachycardia (HR ⩾ 100 bpm). MAIN RESULTS: The algorithm obtained official Challenge F1 scores of 0.80 (Overall), 0.90 (Normal), 0.81 (AF), 0.70 (Other), and 0.54 (Noise) on the hidden Challenge test set (3658 ECGs). This is equivalent to a true positive rate (TPR) = 90.1% (Normal), 81.5% (AF), 67.7% (Other), and 69.5% (Noise), and a false positive rate (FPR) = 13.6% (Normal), 2.3% (AF), 7.7% (Other), and 1.5% (Noise). SIGNIFICANCE: The top five features, which together contributed to about 94% of the maximal F1 score were ranked: (1) proportion of RR intervals differing by >50 ms from the preceding RR interval; (2) Poincaré plot geometry estimated by the ratio of the minor-to-major semi-axes of the fitted ellipse; (3) P-wave presence in the average beat; (4) mean percentage of the RR interval first differences; and (5) mean correlation of all beats against the average beat. The global rank of feature extraction methods highlighted that HRV alone was able to provide 92.5% of the maximal F1 score (0.74 versus 0.8). The added value of more complex ECG morphology analysis was less significant for Normal, AF, and Other rhythms (+0.02 to 0.08 points) than for Noise (+0.19 points); however, these were indispensable for wearable ECG recording devices with frequent artefact disturbance.

Real-time detection of pathological cardiac events in the electrocardiogram.

The development of accurate and fast methods for real-time electrocardiogram (ECG) analysis is mandatory in handheld fully automated monitoring devices for high-risk cardiac patients. The present work describes a simple software method for fast detection of pathological cardiac events. It implements real-time procedures for QRS detection, interbeat RR-intervals analysis, QRS waveform evaluation and a decision-tree beat classifier. Two QRS descriptors are defined to assess (i) the RR interval deviation from the mean RR interval and (ii) the QRS waveform deviation from the QRS pattern of the sustained rhythm. The calculation of the second parameter requires a specific technique, in order to satisfy the demand for straight signal processing with minimum iterations and small memory size. This technique includes fast and resource efficient estimation of a histogram matrix, which accumulates dynamically the amplitude-temporal distribution of the successive QRS pattern waveforms. The pilot version of the method is developed in Matlab and it is tested with internationally recognized ECG databases. The assessment of the online single lead QRS detector showed sensitivity and positive predictivity of above 99%. The classification rules for detection of pathological ventricular beats were defined empirically by statistical analysis. The attained specificity and sensitivity are about 99.5% and 95.7% for all databases and about 99.81% and 98.87% for the noise free dataset. The method is applicable in low computational cost systems for long-term ECG monitoring, such as intelligent holters, automatic event/alarm recorders or personal devices with intermittent wireless data transfer to a central terminal.