Discriminating electrocardiographic responses to His-bundle pacing using machine learning

Conduction system pacing: how far are we from the "electrical" bypass?

Conduction system pacing is an alternative practice to conventional right ventricular apical pacing. It is a method that maintains physiologic ventricular activation, based on a correct pathophysiological basis, in which the pacing lead bypasses the lesion of the electrical fibers and the electrical impulse transmits through the intact adjacent conduction system. For this reason, it might be reasonably characterized by the term "electrical bypass" compared to the coronary artery bypass in revascularization therapy. In this review, reference is made to the sequence of events in which conventional right ventricular pacing may cause adverse outcomes. Furthermore, there is a reference to alternative strategies and pacing sites. Interest focuses on the modalities for which there are data from the literature, namely for the right ventricular (RV) septal pacing, the His bundle pacing (HBP), and the left bundle branch pacing (LBBP). A more extensive reference is about the HBP, for which there are the most updated data. We analyze the considerations that limit HBP-wide application in three axes, and we also present the data for the implantation and follow-up of these patients. The indications with their most important studies to date are then described in detail, not only in their undoubtedly positive findings but also in their weak aspects, because of which this pacing mode has not yet received a strong recommendation for implementation. Finally, there is a report on LBBP, focusing mainly on its points of differentiation from HBP.

Deep learning classification of capnography waveforms: secondary analysis of the PRODIGY study

Capnography monitors trigger high priority 'no breath' alarms when CO2 measurements do not exceed a given threshold over a specified time-period. False alarms occur when the underlying breathing pattern is stable, but the alarm is triggered when the CO2 value reduces even slightly below the threshold. True 'no breath' events can be falsely classified as breathing if waveform artifact causes an aberrant spike in CO2 values above the threshold. The aim of this study was to determine the accuracy of a deep learning approach to classifying segments of capnography waveforms as either 'breath' or 'no breath'. A post hoc secondary analysis of data from 9 North American sites included in the PRediction of Opioid-induced Respiratory Depression In Patients Monitored by capnoGraphY (PRODIGY) study was conducted. We used a convolutional neural network to classify 15 s capnography waveform segments drawn from a random sample of 400 participants. Loss was calculated over batches of 32 using the binary cross-entropy loss function with weights updated using the Adam optimizer. Internal-external validation was performed by iteratively fitting the model using data from all but one hospital and then assessing its performance in the remaining hospital. The labelled dataset consisted of 10,391 capnography waveform segments. The neural network's accuracy was 0.97, precision was 0.97 and recall was 0.96. Performance was consistent across hospitals in internal-external validation. The neural network could reduce false capnography alarms. Further research is needed to compare the frequency of alarms derived from the neural network with the standard approach.

Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022;3:405-414. [PMID: 36712163 PMCID: PMC9708023 DOI: 10.1093/ehjdh/ztac042]

Aims

Accurately determining atrial arrhythmia mechanisms from a 12-lead electrocardiogram (ECG) can be challenging. Given the high success rate of cavotricuspid isthmus (CTI) ablation, identification of CTI-dependent typical atrial flutter (AFL) is important for treatment decisions and procedure planning. We sought to train a convolutional neural network (CNN) to classify CTI-dependent AFL vs. non-CTI dependent atrial tachycardia (AT), using data from the invasive electrophysiology (EP) study as the gold standard.

Methods and results

We trained a CNN on data from 231 patients undergoing EP studies for atrial tachyarrhythmia. A total of 13 500 five-second 12-lead ECG segments were used for training. Each case was labelled CTI-dependent AFL or non-CTI-dependent AT based on the findings of the EP study. The model performance was evaluated against a test set of 57 patients. A survey of electrophysiologists in Europe was undertaken on the same 57 ECGs. The model had an accuracy of 86% (95% CI 0.77-0.95) compared to median expert electrophysiologist accuracy of 79% (range 70-84%). In the two thirds of test set cases (38/57) where both the model and electrophysiologist consensus were in agreement, the prediction accuracy was 100%. Saliency mapping demonstrated atrial activation was the most important segment of the ECG for determining model output.

Conclusion

We describe the first CNN trained to differentiate CTI-dependent AFL from other AT using the ECG. Our model matched and complemented expert electrophysiologist performance. Automated artificial intelligence-enhanced ECG analysis could help guide treatment decisions and plan ablation procedures for patients with organized atrial arrhythmias.

ECG and Pacing Criteria for Differentiating Conduction System Pacing from Myocardial Pacing

During His-Purkinje conduction system (HPS) pacing, it is crucial to confirm capture of the His bundle or left bundle branch versus myocardialonly capture. For this, several methods and criteria for differentiation between non-selective (ns) capture - capture of the HPS and the adjacent myocardium - and myocardial-only capture were developed. HPS capture results in faster and more homogenous depolarisation of the left ventricle than right ventricular septal (RVS) myocardial-only capture. Specifically, the depolarisation of the left ventricle (LV) does not require slow cell-to-cell spread of activation from the right side to the left side of the interventricular septum but begins simultaneously with QRS onset as in native depolarisation. These phenomena greatly influence QRS complex morphology and form the basis of electrocardiographic differentiation between HPS and myocardial paced QRS. Moreover, the HPS and the working myocardium are different tissues within the heart muscle that vary not only in conduction velocities but also in refractoriness and capture thresholds. These last two differences can be exploited for the diagnosis of HPS capture using dynamic pacing manoeuvres, namely differential output pacing, programmed stimulation and burst pacing. This review summarises current knowledge of this subject.

Left ventricular activation time and pattern are preserved with both selective and nonselective His bundle pacing

BACKGROUND

His bundle pacing (HBP) can be achieved in 2 ways: selective HBP (S-HBP), where the His bundle is captured alone, and nonselective HBP (NS-HBP), where local myocardium is also captured, resulting a pre-excited electrocardiogram appearance.

OBJECTIVE

We assessed the impact of this ventricular pre-excitation on left and right ventricular dyssynchrony.

METHODS

We recruited patients who displayed both S-HBP and NS-HBP. We performed noninvasive epicardial electrical mapping for left and right ventricular activation time (LVAT and RVAT) and pattern.

RESULTS

Twenty patients were recruited. In the primary analysis, the mean within-patient change in LVAT from S-HBP to NS-HBP was -5.5 ms (95% confidence interval: -0.6 to -10.4, noninferiority P < .0001). NS-HBP did not prolong RVAT (4.3 ms, -4.0 to 12.8, P = .296) but did prolong QRS duration (QRSd, 22.1 ms, 11.8 to 32.4, P = .0003). In patients with narrow intrinsic QRS (n = 6), NS-HBP preserved LVAT (-2.9 ms, -9.7 to 4.0, P = .331) but prolonged QRS duration (31.4 ms, 22.0 to 40.7, P = .0003) and mean RVAT (16.8 ms, -5.3 to 38.9, P = .108) compared to S-HBP. Activation pattern of the left ventricular surface was unchanged between S-HBP and NS-HBP, but NS-HBP produced early basal right ventricular activation that was not seen in S-HBP.

CONCLUSION

Compared to S-HBP, local myocardial capture during NS-HBP produces pre-excitation of the basal right ventricle resulting in QRS duration prolongation. However, NS-HBP preserves the left ventricular activation time and pattern of S-HBP. Left ventricular dyssynchrony is not an important factor when choosing between S-HBP and NS-HBP in most patients.

Effects of His bundle pacing and right ventricular apex pacing on cardiac electrical and mechanical synchrony and cardiac function in patients with heart failure and atrial fibrillation

OBJECTIVE

To investigate the effects of right ventricular apex pacing and His bundle pacing on cardiac mechanical and electrical synchrony and cardiac function in patients with heart failure and atrial fibrillation.

METHODS

A total of 72 patients with heart failure and atrial fibrillation who received permanent pacemaker implantation in our hospital were randomly divided into two groups, with 36 patients in each group. The control group received the right ventricular apex pacing, and the study group received His bundle pacing. In the two groups, the pacing parameters, cardiac function, cardiac electricity, mechanical synchrony, complications and living quality were compared.

RESULTS

During operation and 12 months after the operation, the study group's pacing threshold was higher than the pacing threshold of the control group (all P<0.001). Compared with that before the procedure, NYHA grade and LVEDD of the two groups 12 months after operation were decreased (all P<0.001), while LVEF and various quality of life scores were increased (all P<0.001). The study group's NYHA grade and LVEDD were lower than those of the control group 12 months after operation (all P<0.001), while the study group's quality of life scores and LVEF were higher than those of the control group (all P<0.001). Twelve months after operation, the study group's QRS width and IVMD were lower than QRS width and IVMD of the control group (all P<0.001). The study group's complication rate was 5.56% (2/36), which was lower than the control group's complication rate (22.22% (8/36), P<0.05).

CONCLUSION

Compared with right ventricular apical pacing, His bundle pacing in the treatment of heart failure with atrial fibrillation can better maintain the cardiac electrical and mechanical synchronization, promote the recovery of cardiac function, improve living quality, and has fewer complications and significant advantages.

Electrocardiographic predictors of successful resynchronization of left bundle branch block by His bundle pacing

BACKGROUND

His bundle pacing (HBP) is an alternative to biventricular pacing (BVP) for delivering cardiac resynchronization therapy (CRT) in patients with heart failure and left bundle branch block (LBBB). It is not known whether ventricular activation times and patterns achieved by HBP are equivalent to intact conduction systems and not all patients with LBBB are resynchronized by HBP.

OBJECTIVE

To compare activation times and patterns of His-CRT with BVP-CRT, LBBB and intact conduction systems.

METHODS

In patients with LBBB, noninvasive epicardial mapping (ECG imaging) was performed during BVP and temporary HBP. Intrinsic activation was mapped in all subjects. Left ventricular activation times (LVAT) were measured and epicardial propagation mapping (EPM) was performed, to visualize epicardial wavefronts. Normal activation pattern and a normal LVAT range were determined from normal subjects.

RESULTS

Forty-five patients were included, 24 with LBBB and LV impairment, and 21 with normal 12-lead ECG and LV function. In 87.5% of patients with LBBB, His-CRT successfully shortened LVAT by ≥10 ms. In 33.3%, His-CRT resulted in complete ventricular resynchronization, with activation times and patterns indistinguishable from normal subjects. EPM identified propagation discontinuity artifacts in 83% of patients with LBBB. This was the best predictor of whether successful resynchronization was achieved by HBP (logarithmic odds ratio, 2.19; 95% confidence interval, 0.07-4.31; p = .04).

CONCLUSION

Noninvasive electrocardiographic mapping appears to identify patients whose LBBB can be resynchronized by HBP. In contrast to BVP, His-CRT may deliver the maximum potential ventricular resynchronization, returning activation times, and patterns to those seen in normal hearts.

His-Purkinje Conduction System Pacing: State of the Art in 2020

Conduction system pacing involves directly stimulating the specialised His-Purkinje cardiac conduction system with the aim of activating the ventricles physiologically, in contrast to the dyssynchronous activation produced by conventional myocardial pacing. Since the first report of permanent His bundle pacing (HBP) in 2000, the stylet-driven technique of its earliest incarnation has been superseded by a more successful stylet-less approach. Widespread uptake has led to a much greater evidence base. Single-centre observational studies have now been supported by large multicentre, international registries, mechanistic studies and the first randomised controlled trials. New evidence has elucidated mechanisms of HBP and illustrated the nature and magnitude of its potential benefits for preventing pacing-induced cardiomyopathy and correcting bundle branch block. Left bundle branch pacing (LBBP) is a newer technique in which the lead is fixed deep into the left side of the intraventricular septum to allow capture of the left bundle, distal to the His bundle. LBBP holds promise as a method for physiological pacing that overcomes some of the fixation, threshold and sensing challenges of HBP. In this state-of-the-art review of His-Purkinje conduction system pacing, the authors assess recent evidence and current practice and explore emerging and future directions in this rapidly evolving field.