Ventricular dyssynchrony imaging, echocardiographic and clinical outcomes of left bundle branch pacing and biventricular pacing.

BACKGROUND: Left bundle branch pacing (LBBP) is a novel physiological pacing technique which may serve as an alternative to cardiac resynchronization therapy (CRT) by biventricular pacing (BVP). This study assessed ventricular activation patterns and echocardiographic and clinical outcomes of LBBP and compared this to BVP. METHODS: Fifty consecutive patients underwent LBBP or BVP for CRT. Ventricular activation mapping was obtained by ultra-high-frequency ECG (UHF-ECG). Functional and echocardiographic outcomes and hospitalization for heart failure and all-cause mortality after one year from implantation were evaluated. RESULTS: LBBP resulted in greater resynchronization vs BVP (QRS width: 170 ± 16 ms to 128 ± 20 ms vs 174 ± 15 to 144 ± 17 ms, p = 0.002 (LBBP vs BVP); e-DYS 81 ± 17 ms to 0 ± 32 ms vs 77 ± 18 to 16 ± 29 ms, p = 0.016 (LBBP vs BVP)). Improvement in LVEF (from 28 ± 8 to 42 ± 10 percent vs 28 ± 9 to 36 ± 12 percent, LBBP vs BVP, p = 0.078) was similar. Improvement in NYHA function class (from 2.4 to 1.5 and from 2.3 to 1.5 (LBBP vs BVP)), hospitalization for heart failure and all-cause mortality were comparable in both groups. CONCLUSIONS: Ventricular dyssynchrony imaging is an appropriate way to gain a better insight into activation patterns of LBBP and BVP. LBBP resulted in greater resynchronization (e-DYS and QRS duration) with comparable improvement in LVEF, NYHA functional class, hospitalization for heart failure and all-cause mortality at one year of follow up.

Timing matters for accurate identification of the epileptogenic zone.

OBJECTIVE: Interictal biomarkers of the epileptogenic zone (EZ) and their use in machine learning models open promising avenues for improvement of epilepsy surgery evaluation. Currently, most studies restrict their analysis to short segments of intracranial EEG (iEEG). METHODS: We used 2381 hours of iEEG data from 25 patients to systematically select 5-minute segments across various interictal conditions. Then, we tested machine learning models for EZ localization using iEEG features calculated within these individual segments or across them and evaluated the performance by the area under the precision-recall curve (PRAUC). RESULTS: On average, models achieved a score of 0.421 (the result of the chance classifier was 0.062). However, the PRAUC varied significantly across the segments (0.323-0.493). Overall, NREM sleep achieved the highest scores, with the best results of 0.493 in N2. When using data from all segments, the model performed significantly better than single segments, except NREM sleep segments. CONCLUSIONS: The model based on a short segment of iEEG recording can achieve similar results as a model based on prolonged recordings. The analyzed segment should, however, be carefully and systematically selected, preferably from NREM sleep. SIGNIFICANCE: Random selection of short iEEG segments may give rise to inaccurate localization of the EZ.

Ultra-High-Frequency ECG in Cardiac Pacing and Cardiac Resynchronization Therapy: From Technical Concept to Clinical Application.

Identifying electrical dyssynchrony is crucial for cardiac pacing and cardiac resynchronization therapy (CRT). The ultra-high-frequency electrocardiography (UHF-ECG) technique allows instantaneous dyssynchrony analyses with real-time visualization. This review explores the physiological background of higher frequencies in ventricular conduction and the translational evolution of UHF-ECG in cardiac pacing and CRT. Although high-frequency components were studied half a century ago, their exploration in the dyssynchrony context is rare. UHF-ECG records ECG signals from eight precordial leads over multiple beats in time. After initial conceptual studies, the implementation of an instant visualization of ventricular activation led to clinical implementation with minimal patient burden. UHF-ECG aids patient selection in biventricular CRT and evaluates ventricular activation during various forms of conduction system pacing (CSP). UHF-ECG ventricular electrical dyssynchrony has been associated with clinical outcomes in a large retrospective CRT cohort and has been used to study the electrophysiological differences between CSP methods, including His bundle pacing, left bundle branch (area) pacing, left ventricular septal pacing and conventional biventricular pacing. UHF-ECG can potentially be used to determine a tailored resynchronization approach (CRT through biventricular pacing or CSP) based on the electrical substrate (true LBBB vs. non-specified intraventricular conduction delay with more distal left ventricular conduction disease), for the optimization of CRT and holds promise beyond CRT for the risk stratification of ventricular arrhythmias.

Ultra-high-frequency ECG volumetric and negative derivative epicardial ventricular electrical activation pattern.

From precordial ECG leads, the conventional determination of the negative derivative of the QRS complex (ND-ECG) assesses epicardial activation. Recently we showed that ultra-high-frequency electrocardiography (UHF-ECG) determines the activation of a larger volume of the ventricular wall. We aimed to combine these two methods to investigate the potential of volumetric and epicardial ventricular activation assessment and thereby determine the transmural activation sequence. We retrospectively analyzed 390 ECG records divided into three groups-healthy subjects with normal ECG, left bundle branch block (LBBB), and right bundle branch block (RBBB) patients. Then we created UHF-ECG and ND-ECG-derived depolarization maps and computed interventricular electrical dyssynchrony. Characteristic spatio-temporal differences were found between the volumetric UHF-ECG activation patterns and epicardial ND-ECG in the Normal, LBBB, and RBBB groups, despite the overall high correlations between both methods. Interventricular electrical dyssynchrony values assessed by the ND-ECG were consistently larger than values computed by the UHF-ECG method. Noninvasively obtained UHF-ECG and ND-ECG analyses describe different ventricular dyssynchrony and the general course of ventricular depolarization. Combining both methods based on standard 12-lead ECG electrode positions allows for a more detailed analysis of volumetric and epicardial ventricular electrical activation, including the assessment of the depolarization wave direction propagation in ventricles.

Interictal invasive very high-frequency oscillations in resting awake state and sleep.

Interictal very high-frequency oscillations (VHFOs, 500-2000 Hz) in a resting awake state seem to be, according to a precedent study of our team, a more specific predictor of a good outcome of the epilepsy surgery compared to traditional interictal high-frequency oscillations (HFOs, 80-500 Hz). In this study, we retested this hypothesis on a larger cohort of patients. In addition, we also collected patients' sleep data and hypothesized that the occurrence of VHFOs in sleep will be greater than in resting state. We recorded interictal invasive electroencephalographic (iEEG) oscillations in 104 patients with drug-resistant epilepsy in a resting state and in 35 patients during sleep. 21 patients in the rest study and 11 patients in the sleep study met the inclusion criteria (interictal HFOs and VHFOs present in iEEG recordings, a surgical intervention and a postoperative follow-up of at least 1 year) for further evaluation of iEEG data. In the rest study, patients with good postoperative outcomes had significantly higher ratio of resected contacts with VHFOs compared to HFOs. In sleep, VHFOs were more abundant than in rest and the percentage of resected contacts in patients with good and poor outcomes did not considerably differ in any type of oscillations. In conclusion, (1) our results confirm, in a larger patient cohort, our previous work about VHFOs being a specific predictor of the area which needs to be resected; and (2) that more frequent sleep VHFOs do not further improve the results.

Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis.

Objective.The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data.Approach.We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification.Main results.Our method improved the macroF1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively.Significance.By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test,p≪ 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.

Left bundle branch area pacing results in more physiological ventricular activation than biventricular pacing in patients with left bundle branch block heart failure.

Biventricular pacing (Biv) and left bundle branch area pacing (LBBAP) are methods of cardiac resynchronization therapy (CRT). Currently, little is known about how they differ in terms of ventricular activation. This study compared ventricular activation patterns in left bundle branch block (LBBB) heart failure patients using an ultra-high-frequency electrocardiography (UHF-ECG). This was a retrospective analysis including 80 CRT patients from two centres. UHF-ECG data were obtained during LBBB, LBBAP, and Biv. Left bundle branch area pacing patients were divided into non-selective left bundle branch pacing (NSLBBP) or left ventricular septal pacing (LVSP) and into groups with V6 R-wave peak times (V6RWPT) < 90 ms and ≥ 90 ms. Calculated parameters were: e-DYS (time difference between the first and last activation in V1-V8 leads) and Vdmean (average of V1-V8 local depolarization durations). In LBBB patients (n = 80) indicated for CRT, spontaneous rhythms were compared with Biv (39) and LBBAP rhythms (64). Although both Biv and LBBAP significantly reduced QRS duration (QRSd) compared with LBBB (from 172 to 148 and 152 ms, respectively, both P < 0.001), the difference between them was not significant (P = 0.2). Left bundle branch area pacing led to shorter e-DYS (24 ms) than Biv (33 ms; P = 0.008) and shorter Vdmean (53 vs. 59 ms; P = 0.003). No differences in QRSd, e-DYS, or Vdmean were found between NSLBBP, LVSP, and LBBAP with paced V6RWPTs < 90 and ≥ 90 ms. Both Biv CRT and LBBAP significantly reduce ventricular dyssynchrony in CRT patients with LBBB. Left bundle branch area pacing is associated with more physiological ventricular activation.

Bipolar anodal septal pacing with direct LBB capture preserves physiological ventricular activation better than unipolar left bundle branch pacing.

Background: Left bundle branch pacing (LBBP) produces delayed, unphysiological activation of the right ventricle. Using ultra-high-frequency electrocardiography (UHF-ECG), we explored how bipolar anodal septal pacing with direct LBB capture (aLBBP) affects the resultant ventricular depolarization pattern. Methods: In patients with bradycardia, His bundle pacing (HBP), unipolar nonselective LBBP (nsLBBP), aLBBP, and right ventricular septal pacing (RVSP) were performed. Timing of local ventricular activation, in leads V1-V8, was displayed using UHF-ECG, and electrical dyssynchrony (e-DYS) was calculated as the difference between the first and last activation. Durations of local depolarizations were determined as the width of the UHF-QRS complex at 50% of its amplitude. Results: aLBBP was feasible in 63 of 75 consecutive patients with successful nsLBBP. aLBBP significantly improved ventricular dyssynchrony (mean -9 ms; 95% CI (-12;-6) vs. -24 ms (-27;-21), ), p < 0.001) and shortened local depolarization durations in V1-V4 (mean differences -7 ms to -5 ms (-11;-1), p < 0.05) compared to nsLBBP. aLBBP resulted in e-DYS -9 ms (-12; -6) vs. e-DYS 10 ms (7;14), p < 0.001 during HBP. Local depolarization durations in V1-V2 during aLBBP were longer than HBP (differences 5-9 ms (1;14), p < 0.05, with local depolarization duration in V1 during aLBBP being the same as during RVSP (difference 2 ms (-2;6), p = 0.52). Conclusion: Although aLBBP improved ventricular synchrony and depolarization duration of the septum and RV compared to unipolar nsLBBP, the resultant ventricular depolarization was still less physiological than during HBP.

Relative entropy is an easy-to-use invasive electroencephalographic biomarker of the epileptogenic zone.

OBJECTIVE: High-frequency oscillations are considered among the most promising interictal biomarkers of the epileptogenic zone in patients suffering from pharmacoresistant focal epilepsy. However, there is no clear definition of pathological high-frequency oscillations, and the existing detectors vary in methodology, performance, and computational costs. This study proposes relative entropy as an easy-to-use novel interictal biomarker of the epileptic tissue. METHODS: We evaluated relative entropy and high-frequency oscillation biomarkers on intracranial electroencephalographic data from 39 patients with seizure-free postoperative outcome (Engel Ia) from three institutions. We tested their capability to localize the epileptogenic zone, defined as resected contacts located in the seizure onset zone. The performance was compared using areas under the receiver operating curves (AUROCs) and precision-recall curves. Then we tested whether a universal threshold can be used to delineate the epileptogenic zone across patients from different institutions. RESULTS: Relative entropy in the ripple band (80-250 Hz) achieved an average AUROC of .85. The normalized high-frequency oscillation rate in the ripple band showed an identical AUROC of .85. In contrast to high-frequency oscillations, relative entropy did not require any patient-level normalization and was easy and fast to calculate due to its clear and straightforward definition. One threshold could be set across different patients and institutions, because relative entropy is independent of signal amplitude and sampling frequency. SIGNIFICANCE: Although both relative entropy and high-frequency oscillations have a similar performance, relative entropy has significant advantages such as straightforward definition, computational speed, and universal interpatient threshold, making it an easy-to-use promising biomarker of the epileptogenic zone.

Utilization of temporal autoencoder for semi-supervised intracranial EEG clustering and classification.

Manual visual review, annotation and categorization of electroencephalography (EEG) is a time-consuming task that is often associated with human bias and requires trained electrophysiology experts with specific domain knowledge. This challenge is now compounded by development of measurement technologies and devices allowing large-scale heterogeneous, multi-channel recordings spanning multiple brain regions over days, weeks. Currently, supervised deep-learning techniques were shown to be an effective tool for analyzing big data sets, including EEG. However, the most significant caveat in training the supervised deep-learning models in a clinical research setting is the lack of adequate gold-standard annotations created by electrophysiology experts. Here, we propose a semi-supervised machine learning technique that utilizes deep-learning methods with a minimal amount of gold-standard labels. The method utilizes a temporal autoencoder for dimensionality reduction and a small number of the expert-provided gold-standard labels used for kernel density estimating (KDE) maps. We used data from electrophysiological intracranial EEG (iEEG) recordings acquired in two hospitals with different recording systems across 39 patients to validate the method. The method achieved iEEG classification (Pathologic vs. Normal vs. Artifacts) results with an area under the receiver operating characteristic (AUROC) scores of 0.862 ± 0.037, 0.879 ± 0.042, and area under the precision-recall curve (AUPRC) scores of 0.740 ± 0.740, 0.714 ± 0.042. This demonstrates that semi-supervised methods can provide acceptable results while requiring only 100 gold-standard data samples in each classification category. Subsequently, we deployed the technique to 12 novel patients in a pseudo-prospective framework for detecting Interictal epileptiform discharges (IEDs). We show that the proposed temporal autoencoder was able to generalize to novel patients while achieving AUROC of 0.877 ± 0.067 and AUPRC of 0.705 ± 0.154.

Shadows of very high-frequency oscillations can be detected in lower frequency bands of routine stereoelectroencephalography.

Very high-frequency oscillations (VHFOs, > 500 Hz) are more specific in localizing the epileptogenic zone (EZ) than high-frequency oscillations (HFOs, < 500 Hz). Unfortunately, VHFOs are not visible in standard clinical stereo-EEG (SEEG) recordings with sampling rates of 1 kHz or lower. Here we show that "shadows" of VHFOs can be found in frequencies below 500 Hz and can help us to identify SEEG channels with a higher probability of increased VHFO rates. Subsequent analysis of Logistic regression models on 141 SEEG channels from thirteen patients shows that VHFO "shadows" provide additional information to gold standard HFO analysis and can potentially help in precise EZ delineation in standard clinical recordings.

Ventricular Dyssynchrony and Pacing-induced Cardiomyopathy in Patients with Pacemakers, the Utility of Ultra-high-frequency ECG and Other Dyssynchrony Assessment Tools.

The majority of patients tolerate right ventricular pacing well; however, some patients manifest signs of heart failure after pacemaker implantation and develop pacing-induced cardiomyopathy. This is a consequence of non-physiological ventricular activation bypassing the conduction system. Ventricular dyssynchrony was identified as one of the main factors responsible for pacing-induced cardiomyopathy development. Currently, methods that would allow rapid and reliable ventricular dyssynchrony assessment, ideally during the implant procedure, are lacking. Paced QRS duration is an imperfect marker of dyssynchrony, and methods based on body surface mapping, electrocardiographic imaging or echocardiography are laborious and time-consuming, and can be difficult to use during the implantation procedure. However, the ventricular activation sequence can be readily displayed from the chest leads using an ultra-high-frequency ECG. It can be performed during the implantation procedure to visualise ventricular depolarisation and resultant ventricular dyssynchrony during pacing. This information can assist the electrophysiologist in selecting a pacing location that avoids dyssynchronous ventricular activation.

QRS detection and classification in Holter ECG data in one inference step.

While various QRS detection and classification methods were developed in the past, the Holter ECG data acquired during daily activities by wearable devices represent new challenges such as increased noise and artefacts due to patient movements. Here, we present a deep-learning model to detect and classify QRS complexes in single-lead Holter ECG. We introduce a novel approach, delivering QRS detection and classification in one inference step. We used a private dataset (12,111 Holter ECG recordings, length of 30 s) for training, validation, and testing the method. Twelve public databases were used to further test method performance. We built a software tool to rapidly annotate QRS complexes in a private dataset, and we annotated 619,681 QRS complexes. The standardised and down-sampled ECG signal forms a 30-s long input for the deep-learning model. The model consists of five ResNet blocks and a gated recurrent unit layer. The model's output is a 30-s long 4-channel probability vector (no-QRS, normal QRS, premature ventricular contraction, premature atrial contraction). Output probabilities are post-processed to receive predicted QRS annotation marks. For the QRS detection task, the proposed method achieved the F1 score of 0.99 on the private test set. An overall mean F1 cross-database score through twelve external public databases was 0.96 ± 0.06. In terms of QRS classification, the presented method showed micro and macro F1 scores of 0.96 and 0.74 on the private test set, respectively. Cross-database results using four external public datasets showed micro and macro F1 scores of 0.95 ± 0.03 and 0.73 ± 0.06, respectively. Presented results showed that QRS detection and classification could be reliably computed in one inference step. The cross-database tests showed higher overall QRS detection performance than any of compared methods.

Classification of ECG using ensemble of residual CNNs with or without attention mechanism.

Objective. This paper introduces a winning solution (team ISIBrno-AIMT) to the official round of PhysioNet Challenge 2021. The main goal of the challenge was a classification of ECG recordings into 26 multi-label pathological classes with a variable number of leads (e.g. 12, 6, 4, 3, 2). The main objective of this study is to verify whether the multi-head-attention mechanism influences the model performance.Approach. We introduced an ECG classification method based on the ResNet architecture with a multi-head attention mechanism for the official round of the challenge. However, empirical findings collected during model development suggested that the multi-head attention layer might not significantly impact the final classification performance. For this reason, during the follow-up round, we removed a multi-head attention layer to test the influence on model performance. Like the official round, the model is optimized using a mixture of loss functions, i.e. binary cross-entropy, custom challenge score loss function, and custom sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final architecture consists of three submodels forming a majority voting classification ensemble.Main results. The modified model without the multi-head attention layer increased the overall challenge score to 0.59 compared to the 0.58 from the official round.Significance. Our findings from the follow-up submission support the fact that the multi-head attention layer in the proposed architecture does not significantly affect the classification performance.

Arterial Aging Best Reflected in Pulse Wave Velocity Measured from Neck to Lower Limbs: A Whole-Body Multichannel Bioimpedance Study.

Pulse wave velocity is a commonly used parameter for evaluating arterial stiffness and the overall condition of the cardiovascular system. The main goal of this study was to establish a methodology to test and validate multichannel bioimpedance as a suitable method for whole-body evaluations of pulse waves. We set the proximal location over the left carotid artery and eight distal locations on both the upper and lower limbs. In this way, it was possible to simultaneously evaluate pulse wave velocity (PWV) in the upper and lower limbs and in the limbs via four extra PWV measurements. Data were acquired from a statistical group of 220 healthy subjects who were divided into three age groups. The data were then analysed. We found a significant dependency of aortic PWV on age in those values measured using the left carotid as the proximal. PWV values in the upper and lower limbs were found to have no significant dependency on age. In addition, the PWV in the left femoral artery shows comparable values to published already carotid-femoral values. Those findings prove the reliability of whole-body multichannel bioimpedance for pulse wave velocity evaluation and provide reference values for whole-body PWV measurement.

Electrical brain stimulation and continuous behavioral state tracking in ambulatory humans.

Objective.Electrical deep brain stimulation (DBS) is an established treatment for patients with drug-resistant epilepsy. Sleep disorders are common in people with epilepsy, and DBS may actually further disturb normal sleep patterns and sleep quality. Novel implantable devices capable of DBS and streaming of continuous intracranial electroencephalography (iEEG) signals enable detailed assessments of therapy efficacy and tracking of sleep related comorbidities. Here, we investigate the feasibility of automated sleep classification using continuous iEEG data recorded from Papez's circuit in four patients with drug resistant mesial temporal lobe epilepsy using an investigational implantable sensing and stimulation device with electrodes implanted in bilateral hippocampus (HPC) and anterior nucleus of thalamus (ANT).Approach.The iEEG recorded from HPC is used to classify sleep during concurrent DBS targeting ANT. Simultaneous polysomnography (PSG) and sensing from HPC were used to train, validate and test an automated classifier for a range of ANT DBS frequencies: no stimulation, 2 Hz, 7 Hz, and high frequency (>100 Hz).Main results.We show that it is possible to build a patient specific automated sleep staging classifier using power in band features extracted from one HPC iEEG sensing channel. The patient specific classifiers performed well under all thalamic DBS frequencies with an average F1-score 0.894, and provided viable classification into awake and major sleep categories, rapid eye movement (REM) and non-REM. We retrospectively analyzed classification performance with gold-standard PSG annotations, and then prospectively deployed the classifier on chronic continuous iEEG data spanning multiple months to characterize sleep patterns in ambulatory patients living in their home environment.Significance.The ability to continuously track behavioral state and fully characterize sleep should prove useful for optimizing DBS for epilepsy and associated sleep, cognitive and mood comorbidities.

Ultra-fast oscillation detection in EEG signal from deep-brain microelectrodes.

For the last decades, ripples 80-200Hz (R)and fast ripples 200-500Hz (FR) were intensively studied as biomarkers of the epileptogenic zone (EZ). Recently, Very fast ripples 500-1000Hz (VFR) and ultra-fast ripples 1000-2000Hz (UFR) recorded using standard clinical macro electrodes have been shown to be more specific for EZ. High-sampled microelectrode recordings can bring new insights into this phenomenon of high frequency, multiunit activity. Unfortunately, visual detection of such events is extremely time consuming and unreliable. Here we present a detector of ultra-fast oscillations (UFO, >1kHz). In an example of two patients, we detected 951 UFOs which were more frequent in epileptic (8.6/min) vs. non-epileptic hippocampus (1.3/min). Our detection method can serve as a tool for exploring extremely high frequency events from microelectrode recordings.