Detection of acute coronary occlusion with a novel mobile electrocardiogram device: a pilot study

Aims

Many portable electrocardiogram (ECG) devices have been developed to monitor patients at home, but the majority of these devices are single lead and only intended for rhythm disorders. We developed the miniECG, a smartphone-sized portable device with four dry electrodes capable of recording a high-quality multi-lead ECG by placing the device on the chest. The aim of our study was to investigate the ability of the miniECG to detect occlusive myocardial infarction (OMI) in patients with chest pain.

Methods and results

Patients presenting with acute chest pain at the emergency department of the University Medical Center Utrecht or Meander Medical Center, between May 2021 and February 2022, were included in the study. The clinical 12-lead ECG and the miniECG before coronary intervention were recorded. The recordings were evaluated by cardiologists and compared the outcome of the coronary angiography, if performed. A total of 369 patients were measured with the miniECG, 46 of whom had OMI. The miniECG detected OMI with a sensitivity and specificity of 65 and 92%, compared with 83 and 90% for the 12-lead ECG. Sensitivity of the miniECG was similar for different culprit vessels.

Conclusion

The miniECG can record a multi-lead ECG and rule-in ST-segment deviation in patients with occluded or near-occluded coronary arteries from different culprit vessels without many false alarms. Further research is required to add automated analysis to the recordings and to show feasibility to use the miniECG by patients at home.

ECG-only explainable deep learning algorithm predicts the risk for malignant ventricular arrhythmia in phospholamban cardiomyopathy

BACKGROUND

Phospholamban (PLN) p.(Arg14del) variant carriers are at risk for development of malignant ventricular arrhythmia (MVA). Accurate risk stratification allows timely implantation of intracardiac defibrillators and is currently performed with a multimodality prediction model.

OBJECTIVE

This study aimed to investigate whether an explainable deep learning-based approach allows risk prediction with only electrocardiogram (ECG) data.

METHODS

A total of 679 PLN p.(Arg14del) carriers without MVA at baseline were identified. A deep learning-based variational auto-encoder, trained on 1.1 million ECGs, was used to convert the 12-lead baseline ECG into its FactorECG, a compressed version of the ECG that summarizes it into 32 explainable factors. Prediction models were developed by Cox regression.

RESULTS

The deep learning-based ECG-only approach was able to predict MVA with a C statistic of 0.79 (95% CI, 0.76-0.83), comparable to the current prediction model (C statistic, 0.83 [95% CI, 0.79-0.88]; P = .054) and outperforming a model based on conventional ECG parameters (low-voltage ECG and negative T waves; C statistic, 0.65 [95% CI, 0.58-0.73]; P < .001). Clinical simulations showed that a 2-step approach, with ECG-only screening followed by a full workup, resulted in 60% less additional diagnostics while outperforming the multimodal prediction model in all patients. A visualization tool was created to provide interactive visualizations (https://pln.ecgx.ai).

CONCLUSION

Our deep learning-based algorithm based on ECG data only accurately predicts the occurrence of MVA in PLN p.(Arg14del) carriers, enabling more efficient stratification of patients who need additional diagnostic testing and follow-up.

ANOCA patients with and without coronary vasomotor dysfunction present with limited electrocardiographic remodeling

Background

Coronary vasomotor dysfunction (CVDys) comprises coronary vasospasm (CVS) and/or coronary microvascular dysfunction (CMD) and is highly prevalent in patients with angina and non-obstructive coronary artery disease (ANOCA). Invasive coronary function testing (CFT) to diagnose CVDys is becoming more common, enabling pathophysiologic research of CVDys. This study aims to explore the electrophysiological characteristics of ANOCA patients with CVDys.

Methods

We collected pre-procedural 12-lead electrocardiograms of ANOCA patients with CVS (n = 35), CMD (n = 24), CVS/CMD (n = 26) and patients without CVDys (CFT-, n = 23) who participated in the NL-CFT registry and underwent CFT. Heart axis and conduction times were compared between patients with CVS, CMD or CVS/CMD and patients without CVDys.

Results

Heart axis, heart rate, PQ interval and QRS duration were comparable between the groups. A small prolongation of the QT-interval corrected with Bazett (QTcB) and Fridericia (QTcF) was observed in patients with CVDys compared to patients without CVDys (CVS vs CFT-: QTcB = 422 ± 18 vs 414 ± 18 ms (p = 0.14), QTcF = 410 ± 14 vs 406 ± 12 ms (p = 0.21); CMD vs CFT-: QTcB = 426 ± 17 vs 414 ± 18 ms (p = 0.03), QTcF = 413 ± 11 vs 406 ± 12 ms (p = 0.04); CVS/CMD vs CFT-: QTcB = 424 ± 17 vs 414 ± 18 ms (p = 0.05), QTcF = 414 ± 14 vs 406 ± 12 ms (p = 0.04)).

Conclusions

Pre-procedural 12-lead electrocardiograms were comparable between patients with and without CVDys undergoing CFT except for a slightly longer QTc interval in patients with CVDys compared to patients without CVDys, suggesting limited cardiac remodeling in patients with CVDys.

Automatic triage of twelve-lead electrocardiograms using deep convolutional neural networks: a first implementation study

Aims

Expert knowledge to correctly interpret electrocardiograms (ECGs) is not always readily available. An artificial intelligence (AI)-based triage algorithm (DELTAnet), able to support physicians in ECG prioritization, could help reduce current logistic burden of overreading ECGs and improve time to treatment for acute and life-threatening disorders. However, the effect of clinical implementation of such AI algorithms is rarely investigated.

Methods and results

Adult patients at non-cardiology departments who underwent ECG testing as a part of routine clinical care were included in this prospective cohort study. DELTAnet was used to classify 12-lead ECGs into one of the following triage classes: normal, abnormal not acute, subacute, and acute. Performance was compared with triage classes based on the final clinical diagnosis. Moreover, the associations between predicted classes and clinical outcomes were investigated. A total of 1061 patients and ECGs were included. Performance was good with a mean concordance statistic of 0.96 (95% confidence interval 0.95-0.97) when comparing DELTAnet with the clinical triage classes. Moreover, zero ECGs that required a change in policy or referral to the cardiologist were missed and there was a limited number of cases predicted as acute that did not require follow-up (2.6%).

Conclusion

This study is the first to prospectively investigate the impact of clinical implementation of an ECG-based AI triage algorithm. It shows that DELTAnet is efficacious and safe to be used in clinical practice for triage of 12-lead ECGs in non-cardiology hospital departments.

Deep neural network-based clustering of deformation curves reveals novel disease features in PLN pathogenic variant carriers

Echocardiographic deformation curves provide detailed information on myocardial function. Deep neural networks (DNNs) may enable automated detection of disease features in deformation curves, and improve the clinical assessment of these curves. We aimed to investigate whether an explainable DNN-based pipeline can be used to detect and visualize disease features in echocardiographic deformation curves of phospholamban (PLN) p.Arg14del variant carriers. A DNN was trained to discriminate PLN variant carriers (n = 278) from control subjects (n = 621) using raw deformation curves obtained by 2D-speckle tracking in the longitudinal axis. A visualization technique was used to identify the parts of these curves that were used by the DNN for classification. The PLN variant carriers were clustered according to the output of the visualization technique. The DNN showed excellent discriminatory performance (C-statistic 0.93 [95% CI 0.87-0.97]). We identified four clusters with PLN-associated disease features in the deformation curves. Two clusters showed previously described features: apical post-systolic shortening and reduced systolic strain. The two other clusters revealed novel features, both reflecting delayed relaxation. Additionally, a fifth cluster was identified containing variant carriers without disease features in the deformation curves, who were classified as controls by the DNN. This latter cluster had a very benign disease course regarding development of ventricular arrhythmias. Applying an explainable DNN-based pipeline to myocardial deformation curves enables automated detection and visualization of disease features. In PLN variant carriers, we discovered novel disease features which may improve individual risk stratification. Applying this approach to other diseases will further expand our knowledge on disease-specific deformation patterns. Overview of the deep neural network-based pipeline for feature detection in myocardial deformation curves. Firstly, phospholamban (PLN) p.Arg14del variant carriers and controls were selected and a deep neural network (DNN) was trained to detect the PLN variant carriers. Subsequently, a clustering-based approach was performed on the attention maps of the DNN, which revealed 4 distinct phenotypes of PLN variant carriers with different prognoses. Moreover, a cluster without features and a benign prognosis was detected.

Machine-learning-derived heart and brain age are independently associated with cognition

BACKGROUND AND PURPOSE

A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated.

METHODS

Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40-85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis.

RESULTS

Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3-36) of the HDA effect on the tapping test score was mediated through BDA.

DISCUSSION

Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Electrocardiogram Devices for Home Use: Technological and Clinical Scoping Review

BACKGROUND

Electrocardiograms (ECGs) are used by physicians to record, monitor, and diagnose the electrical activity of the heart. Recent technological advances have allowed ECG devices to move out of the clinic and into the home environment. There is a great variety of mobile ECG devices with the capabilities to be used in home environments.

OBJECTIVE

This scoping review aimed to provide a comprehensive overview of the current landscape of mobile ECG devices, including the technology used, intended clinical use, and available clinical evidence.

METHODS

We conducted a scoping review to identify studies concerning mobile ECG devices in the electronic database PubMed. Secondarily, an internet search was performed to identify other ECG devices available in the market. We summarized the devices' technical information and usability characteristics based on manufacturer data such as datasheets and user manuals. For each device, we searched for clinical evidence on the capabilities to record heart disorders by performing individual searches in PubMed and ClinicalTrials.gov, as well as the Food and Drug Administration (FDA) 510(k) Premarket Notification and De Novo databases.

RESULTS

From the PubMed database and internet search, we identified 58 ECG devices with available manufacturer information. Technical characteristics such as shape, number of electrodes, and signal processing influence the capabilities of the devices to record cardiac disorders. Of the 58 devices, only 26 (45%) had clinical evidence available regarding their ability to detect heart disorders such as rhythm disorders, more specifically atrial fibrillation.

CONCLUSIONS

ECG devices available in the market are mainly intended to be used for the detection of arrhythmias. No devices are intended to be used for the detection of other cardiac disorders. Technical and design characteristics influence the intended use of the devices and use environments. For mobile ECG devices to be intended to detect other cardiac disorders, challenges regarding signal processing and sensor characteristics should be solved to increase their detection capabilities. Devices recently released include the use of other sensors on ECG devices to increase their detection capabilities.

Feasibility of Linear Irreversible Electroporation Ablation in the Coronary Sinus

INTRODUCTION

Previous studies demonstrated that the coronary sinus (CS) is an important target for ablation in persistent atrial fibrillation. However, radiofrequency ablation in the CS is associated with coronary vessel damage and tamponade. Animal data suggest irreversible electroporation (IRE) ablation can be a safe ablation modality in vicinity of coronary arteries. We investigated the feasibility of IRE in the CS in a porcine model.

METHODS

Ablation and pacing was performed in the CS in six pigs (weight 60-75 kg) using a modified 9-French steerable linear hexapolar Tip-Versatile Ablation Catheter. Pacing maneuvers were performed from distal to proximal segments of the CS to assess atrial capture thresholds before and after IRE application. IRE ablations were performed with 100 J IRE pulses. After 3-week survival animals were euthanized and histological sections from the CS were analyzed.

RESULTS

A total of 27 IRE applications in six animals were performed. Mean peak voltage was 1509 ± 36 V, with a mean peak current of 22.9 ± 1.0 A. No complications occurred during procedure and 3-week survival. At 30 min post ablation 100% isolation was achieved in all animals. At 3 weeks follow-up pacing thresholds were significant higher as compared to baseline. Histological analysis showed transmural ablation lesions in muscular sleeves surrounding the CS.

CONCLUSION

IRE ablation of the musculature along the CS using a multi-electrode catheter is feasible in a porcine model.

Electrocardiogram-based deep learning improves outcome prediction following cardiac resynchronization therapy

AIMS

This study aims to identify and visualize electrocardiogram (ECG) features using an explainable deep learning-based algorithm to predict cardiac resynchronization therapy (CRT) outcome. Its performance is compared with current guideline ECG criteria and QRSAREA.

METHODS AND RESULTS

A deep learning algorithm, trained on 1.1 million ECGs from 251 473 patients, was used to compress the median beat ECG, thereby summarizing most ECG features into only 21 explainable factors (FactorECG). Pre-implantation ECGs of 1306 CRT patients from three academic centres were converted into their respective FactorECG. FactorECG predicted the combined clinical endpoint of death, left ventricular assist device, or heart transplantation [c-statistic 0.69, 95% confidence interval (CI) 0.66-0.72], significantly outperforming QRSAREA and guideline ECG criteria [c-statistic 0.61 (95% CI 0.58-0.64) and 0.57 (95% CI 0.54-0.60), P < 0.001 for both]. The addition of 13 clinical variables was of limited added value for the FactorECG model when compared with QRSAREA (Δ c-statistic 0.03 vs. 0.10). FactorECG identified inferolateral T-wave inversion, smaller right precordial S- and T-wave amplitude, ventricular rate, and increased PR interval and P-wave duration to be important predictors for poor outcome. An online visualization tool was created to provide interactive visualizations (https://crt.ecgx.ai).

CONCLUSION

Requiring only a standard 12-lead ECG, FactorECG held superior discriminative ability for the prediction of clinical outcome when compared with guideline criteria and QRSAREA, without requiring additional clinical variables. End-to-end automated visualization of ECG features allows for an explainable algorithm, which may facilitate rapid uptake of this personalized decision-making tool in CRT.

Multielectrode Contact Measurement Can Improve Long-Term Outcome of Pulmonary Vein Isolation Using Circular Single-Pulse Electroporation Ablation

BACKGROUND

Irreversible electroporation (IRE) ablation is generally performed with multielectrode catheters. Electrode-tissue contact is an important predictor for the success of pulmonary vein (PV) isolation; however, contact force is difficult to measure with multielectrode ablation catheters. In a preclinical study, we assessed the feasibility of a multielectrode impedance system (MEIS) as a predictor of long-term success of PV isolation. In addition, we present the first-in-human clinical experience with MEIS.

METHODS

In 10 pigs, one PV was ablated based on impedance (MEIS group), and the other PV was solely based on local electrogram information (electrophysiological group). IRE ablations were performed at 200 J. After 3 months, recurrence of conduction was assessed. Subsequently, in 30 patients undergoing PV isolation with IRE, MEIS was evaluated and MEIS contact values were compared to local electrograms.

RESULTS

In the porcine study, 43 IRE applications were delivered in 19 PVs. Acutely, no reconnections were observed in either group. After 3 months, 0 versus 3 (P=0.21) PVs showed conduction recurrence in the MEIS and electrophysiological groups, respectively. Results from the clinical study showed a significant linear relation was found between mean MEIS value and bipolar dV/dt (r²=0.49, P<0.001), with a slope of 20.6 mV/s per Ohm.

CONCLUSIONS

Data from the animal study suggest that MEIS values predict effective IRE applications. For the long-term success of electrical PV isolation with circular IRE applications, no significant difference in efficacy was found between ablation based on the measurement of electrode interface impedance and ablation using the classical electrophysiological approach for determining electrode-tissue contact. Experiences of the first clinical use of MEIS were promising and serve as an important basis for future research.

Improving explainability of deep neural network-based electrocardiogram interpretation using variational auto-encoders. Eur Heart J Digit Health 2022;3:390-404. [PMID: 36712164 PMCID: PMC9707974 DOI: 10.1093/ehjdh/ztac038]

Aims

Deep neural networks (DNNs) perform excellently in interpreting electrocardiograms (ECGs), both for conventional ECG interpretation and for novel applications such as detection of reduced ejection fraction (EF). Despite these promising developments, implementation is hampered by the lack of trustworthy techniques to explain the algorithms to clinicians. Especially, currently employed heatmap-based methods have shown to be inaccurate.

Methods and results

We present a novel pipeline consisting of a variational auto-encoder (VAE) to learn the underlying factors of variation of the median beat ECG morphology (the FactorECG), which are subsequently used in common and interpretable prediction models. As the ECG factors can be made explainable by generating and visualizing ECGs on both the model and individual level, the pipeline provides improved explainability over heatmap-based methods. By training on a database with 1.1 million ECGs, the VAE can compress the ECG into 21 generative ECG factors, most of which are associated with physiologically valid underlying processes. Performance of the explainable pipeline was similar to 'black box' DNNs in conventional ECG interpretation [area under the receiver operating curve (AUROC) 0.94 vs. 0.96], detection of reduced EF (AUROC 0.90 vs. 0.91), and prediction of 1-year mortality (AUROC 0.76 vs. 0.75). Contrary to the 'black box' DNNs, our pipeline provided explainability on which morphological ECG changes were important for prediction. Results were confirmed in a population-based external validation dataset.

Conclusions

Future studies on DNNs for ECGs should employ pipelines that are explainable to facilitate clinical implementation by gaining confidence in artificial intelligence and making it possible to identify biased models.

Life-threatening ventricular arrhythmia prediction in patients with dilated cardiomyopathy using explainable electrocardiogram-based deep neural networks

Aims

While electrocardiogram (ECG) characteristics have been associated with life-threatening ventricular arrhythmias (LTVA) in dilated cardiomyopathy (DCM), they typically rely on human-derived parameters. Deep neural networks (DNNs) can discover complex ECG patterns, but the interpretation is hampered by their ‘black-box’ characteristics. We aimed to detect DCM patients at risk of LTVA using an inherently explainable DNN.

Methods and results

In this two-phase study, we first developed a variational autoencoder DNN on more than 1 million 12-lead median beat ECGs, compressing the ECG into 21 different factors (F): FactorECG. Next, we used two cohorts with a combined total of 695 DCM patients and entered these factors in a Cox regression for the composite LTVA outcome, which was defined as sudden cardiac arrest, spontaneous sustained ventricular tachycardia, or implantable cardioverter-defibrillator treated ventricular arrhythmia. Most patients were male (n = 442, 64%) with a median age of 54 years [interquartile range (IQR) 44–62], and median left ventricular ejection fraction of 30% (IQR 23–39). A total of 115 patients (16.5%) reached the study outcome. Factors F₈ (prolonged PR-interval and P-wave duration, P < 0.005), F₁₅ (reduced P-wave height, P = 0.04), F₂₅ (increased right bundle branch delay, P = 0.02), F₂₇ (P-wave axis P < 0.005), and F₃₂ (reduced QRS-T voltages P = 0.03) were significantly associated with LTVA.

Conclusion

Inherently explainable DNNs can detect patients at risk of LTVA which is mainly driven by P-wave abnormalities.

Safety and feasibility study of non-invasive robot-assisted high-intensity focused ultrasound therapy for the treatment of atherosclerotic plaques in the femoral artery: protocol for a pilot study

INTRODUCTION

Peripheral arterial disease (PAD) is an atherosclerotic disease leading to stenosis and/or occlusion of the arterial circulation of the lower extremities. The currently available revascularisation methods have an acceptable initial success rate, but the long-term patency is limited, while surgical revascularisation is associated with a relatively high perioperative risk. This urges the need for development of less invasive and more effective treatment modalities. This protocol article describes a study investigating a new non-invasive technique that uses robot assisted high-intensity focused ultrasound (HIFU) to treat atherosclerosis in the femoral artery.

METHODS AND ANALYSIS

A pilot study is currently performed in 15 symptomatic patients with PAD with a significant stenosis in the common femoral and/or proximal superficial femoral artery. All patients will be treated with the dual-mode ultrasound array system to deliver imaging-guided HIFU to the atherosclerotic plaque. Safety and feasibility are the primary objectives assessed by the technical feasibility of this therapy and the 30-day major complication rate as primary endpoints. Secondary endpoints are angiographic and clinical success and quality of life.

ETHICS AND DISSEMINATION

Ethical approval for this study was obtained in 2019 from the Medical Ethics Committee of the University Medical Center Utrecht, the Netherlands. Data will be presented at national and international conferences and published in a peer-reviewed journal.

TRIAL REGISTRATION NUMBER

NL7564.

Deep neural networks reveal novel sex-specific electrocardiographic features relevant for mortality risk

Aims

Incorporation of sex in study design can lead to discoveries in medical research. Deep neural networks (DNNs) accurately predict sex based on the electrocardiogram (ECG) and we hypothesized that misclassification of sex is an important predictor for mortality. Therefore, we first developed and validated a DNN that classified sex based on the ECG and investigated the outcome. Second, we studied ECG drivers of DNN-classified sex and mortality.

Methods and results

A DNN was trained to classify sex based on 131 673 normal ECGs. The algorithm was validated on internal (68 500 ECGs) and external data sets (3303 and 4457 ECGs). The survival of sex (mis)classified groups was investigated using time-to-event analysis and sex-stratified mediation analysis of ECG features. The DNN successfully distinguished female from male ECGs {internal validation: area under the curve (AUC) 0.96 [95% confidence interval (CI): 0.96, 0.97]; external validations: AUC 0.89 (95% CI: 0.88, 0.90), 0.94 (95% CI: 0.93, 0.94)}. Sex-misclassified individuals (11%) had a 1.4 times higher mortality risk compared with correctly classified peers. The ventricular rate was the strongest mediating ECG variable (41%, 95% CI: 31%, 56%) in males, while the maximum amplitude of the ST segment was strongest in females (18%, 95% CI: 11%, 39%). Short QRS duration was associated with higher mortality risk.

Conclusion

Deep neural networks accurately classify sex based on ECGs. While the proportion of ECG-based sex misclassifications is low, it is an interesting biomarker. Investigation of the causal pathway between misclassification and mortality uncovered new ECG features that might be associated with mortality. Increased emphasis on sex as a biological variable in artificial intelligence is warranted.

Characteristics and time course of acute and chronic myocardial lesion formation after electroporation ablation in the porcine model

INTRODUCTION

Electroporation ablation creates deep and wide myocardial lesions. No data are available on time course and characteristics of acute lesion formation.

METHODS

For the acute phase of myocardial lesion development, 7 pigs were investigated. Single 200J applications were delivered at 4 different epicardial right ventricular sites using a linear suction device, yielding a total of 28 lesions. Timing of applications was designed to yield lesions at 7 time points: 0, 10, 20, 30, 40, 50, 60 minutes, with 4 lesions per time point. After euthanization, lesion characteristics were histologically investigated. For the chronic phase of myocardial lesion development, tissue samples were used from previously conducted studies where tissue was obtained at 3 weeks and 3 months after electroporation ablation.

RESULTS

Acute myocardial lesions induce a necrosis pattern with contraction band necrosis and interstitial edema, immediately present after electroporation ablation. No further histological changes such as hemorrhage or influx of inflammatory cells occurred in the first hour. After 3 weeks, the lesions consisted of sharply demarcated loose connective tissue that further developed to more fibrotic scar tissue after 3 months without additional changes. Within the scar tissue arteries and nerves were unaffected.

CONCLUSION

Electroporation ablation immediately induces contraction band necrosis and edema without additional tissue changes in the first hour. After 3 weeks a sharply demarked scar has been developed that remains stable during follow up of 3 months. This is highly relevant for clinical application of electroporation ablation in terms of the electrophysiological endpoint and waiting period after ablation. This article is protected by copyright. All rights reserved.

Efficacy of multi-electrode linear irreversible electroporation

AIMS

We investigated the efficacy of linear multi-electrode irreversible electroporation (IRE) ablation in a porcine model.

METHODS AND RESULTS

The study was performed in six pigs (weight 60-75 kg). After median sternotomy and opening of the pericardium, a pericardial cradle was formed and filled with blood. A linear seven polar 7-Fr electrode catheter with 2.5 mm electrodes and 2.5 mm inter-electrode spacing was placed in good contact with epicardial tissue. A single IRE application was delivered using 50 J at one site and 100 J at two other sites, in random sequence, using a standard monophasic defibrillator connected to all seven electrodes connected in parallel. The pericardium and thorax were closed and after 3 weeks survival animals were euthanized. A total of 82 histological sections from all 18 electroporation lesions were analysed. A total of seven 50 J and fourteen 100 J epicardial IRE applications were performed. Mean peak voltages at 50 and 100 J were 1079.2 V ± 81.1 and 1609.5 V ± 56.8, with a mean peak current of 15.4 A ± 2.3 and 20.2 A ± 1.7, respectively. Median depth of the 50 and 100 J lesions were 3.2 mm [interquartile range (IQR) 3.1-3.6] and 5.5 mm (IQR 4.6-6.6) (P < 0.001), respectively. Median lesion width of the 50 and 100 J lesions was 3.9 mm (IQR 3.7-4.8) and 5.4 mm (IQR 5.0-6.3), respectively (P < 0.001). Longitudinal sections showed continuous lesions for 100 J applications.

CONCLUSION

Epicardial multi-electrode linear application of IRE pulses is effective in creating continuous deep lesions.

In vivo analysis of the origin and characteristics of gaseous microemboli during catheter-mediated irreversible electroporation

Aims 

Irreversible electroporation (IRE) ablation is a non-thermal ablation method based on the application of direct current between a multi-electrode catheter and skin electrode. The delivery of current through blood leads to electrolysis. Some studies suggest that gaseous (micro)emboli might be associated with myocardial damage and/or (a)symptomatic cerebral ischaemic events. The aim of this study was to compare the amount of gas generated during IRE ablation and during radiofrequency (RF) ablation.

Methods and results

In six 60–75 kg pigs, an extracorporeal femoral shunt was outfitted with a bubble-counter to detect the size and total volume of gas bubbles. Anodal and cathodal 200 J IRE applications were delivered in the left atrium (LA) using a 14-electrode circular catheter. The 30 and 60 s 40 W RF point-by-point ablations were performed. Using transoesophageal echocardiography (TOE), gas formation was visualized. Average gas volumes were 0.6 ± 0.6 and 56.9 ± 19.1 μL (P < 0.01) for each anodal and cathodal IRE application, respectively. Also, qualitative TOE imaging showed significantly less LA bubble contrast with anodal than with cathodal applications. Radiofrequency ablations produced 1.7 ± 2.9 and 6.7 ± 7.4 μL of gas, for 30 and 60 s ablation time, respectively.

Conclusion 

Anodal IRE applications result in significantly less gas formation than both cathodal IRE applications and RF applications. This finding is supported by TOE observations.

Uncertainty estimation for deep learning-based automated analysis of 12-lead electrocardiograms

Aims

Automated interpretation of electrocardiograms (ECGs) using deep neural networks (DNNs) has gained much attention recently. While the initial results have been encouraging, limited attention has been paid to whether such results can be trusted, which is paramount for their clinical implementation. This study aims to systematically investigate uncertainty estimation techniques for automated classification of ECGs using DNNs and to gain insight into its utility through a clinical simulation.

Methods and results

On a total of 526 656 ECGs from three different datasets, six different methods for estimation of aleatoric and epistemic uncertainty were systematically investigated. The methods were evaluated based on ranking, calibration, and robustness against out-of-distribution data. Furthermore, a clinical simulation was performed where increasing uncertainty thresholds were applied to achieve a clinically acceptable performance. Finally, the correspondence between the uncertainty of ECGs and the lack of interpretational agreement between cardiologists was estimated. Results demonstrated the largest benefit when modelling both epistemic and aleatoric uncertainty. Notably, the combination of variational inference with Bayesian decomposition and ensemble with auxiliary output outperformed the other methods. The clinical simulation showed that the accuracy of the algorithm increased as uncertain predictions were referred to the physician. Moreover, high uncertainty in DNN-based ECG classification strongly corresponded with a lower diagnostic agreement in cardiologist's interpretation (P < 0.001).

Conclusion

Uncertainty estimation is warranted in automated DNN-based ECG classification and its accurate estimation enables intermediate quality control in the clinical implementation of deep learning. This is an important step towards the clinical applicability of automated ECG diagnosis using DNNs.

Discovering and Visualizing Disease-Specific Electrocardiogram Features Using Deep Learning: Proof-of-Concept in Phospholamban Gene Mutation Carriers

BACKGROUND

ECG interpretation requires expertise and is mostly based on physician recognition of specific patterns, which may be challenging in rare cardiac diseases. Deep neural networks (DNNs) can discover complex features in ECGs and may facilitate the detection of novel features which possibly play a pathophysiological role in relatively unknown diseases. Using a cohort of PLN (phospholamban) p.Arg14del mutation carriers, we aimed to investigate whether a novel DNN-based approach can identify established ECG features, but moreover, we aimed to expand our knowledge on novel ECG features in these patients.

METHODS

A DNN was developed on 12-lead median beat ECGs of 69 patients and 1380 matched controls and independently evaluated on 17 patients and 340 controls. Differentiating features were visualized using Guided Gradient Class Activation Mapping++. Novel ECG features were tested for their diagnostic value by adding them to a logistic regression model including established ECG features.

RESULTS

The DNN showed excellent discriminatory performance with a c-statistic of 0.95 (95% CI, 0.91-0.99) and sensitivity and specificity of 0.82 and 0.93, respectively. Visualizations revealed established ECG features (low QRS voltages and T-wave inversions), specified these features (eg, R- and T-wave attenuation in V2/V3) and identified novel PLN-specific ECG features (eg, increased PR-duration). The logistic regression baseline model improved significantly when augmented with the identified features (P<0.001).

CONCLUSIONS

A DNN-based feature detection approach was able to discover and visualize disease-specific ECG features in PLN mutation carriers and revealed yet unidentified features. This novel approach may help advance diagnostic capabilities in daily practice.

Big Data and Artificial Intelligence: Opportunities and Threats in Electrophysiology

The combination of big data and artificial intelligence (AI) is having an increasing impact on the field of electrophysiology. Algorithms are created to improve the automated diagnosis of clinical ECGs or ambulatory rhythm devices. Furthermore, the use of AI during invasive electrophysiological studies or combining several diagnostic modalities into AI algorithms to aid diagnostics are being investigated. However, the clinical performance and applicability of created algorithms are yet unknown. In this narrative review, opportunities and threats of AI in the field of electrophysiology are described, mainly focusing on ECGs. Current opportunities are discussed with their potential clinical benefits as well as the challenges. Challenges in data acquisition, model performance, (external) validity, clinical implementation, algorithm interpretation as well as the ethical aspects of AI research are discussed. This article aims to guide clinicians in the evaluation of new AI applications for electrophysiology before their clinical implementation.

Pulmonary Vein Isolation With Single Pulse Irreversible Electroporation

Background:

Irreversible electroporation (IRE) is a promising new nonthermal ablation technology for pulmonary vein (PV) isolation in patients with atrial fibrillation. Experimental data suggest that IRE ablation produces large enough lesions without the risk of PV stenosis, artery, nerve, or esophageal damage. This study aimed to investigate the feasibility and safety of single pulse IRE PV isolation in patients with atrial fibrillation.

Methods:

Ten patients with symptomatic paroxysmal or persistent atrial fibrillation underwent single pulse IRE PV isolation under general anesthesia. Three-dimensional reconstruction and electroanatomical voltage mapping (EnSite Precision, Abbott) of left atrium and PVs were performed using a conventional circular mapping catheter. PV isolation was performed by delivering nonarcing, nonbarotraumatic 6 ms, 200 J direct current IRE applications via a custom nondeflectable 14-polar circular IRE ablation catheter with a variable hoop diameter (16–27 mm). A deflectable sheath (Agilis, Abbott) was used to maneuver the ablation catheter. A minimum of 2 IRE applications with slightly different catheter positions were delivered per vein to achieve circular tissue contact, even if PV potentials were abolished after the first application. Bidirectional PV isolation was confirmed with the circular mapping catheter and a post ablation voltage map. After a 30-minute waiting period, adenosine testing (30 mg) was used to reveal dormant PV conduction.

Results:

All 40 PVs could be successfully isolated with a mean of 2.4±0.4 IRE applications per PV. Mean delivered peak voltage and peak current were 2154±59 V and 33.9±1.6 A, respectively. No PV reconnections occurred during the waiting period and adenosine testing. No periprocedural complications were observed.

Conclusions:

In the 10 patients of this first-in-human study, acute bidirectional electrical PV isolation could be achieved safely by single pulse IRE ablation.

Automatic Triage of 12-Lead ECGs Using Deep Convolutional Neural Networks

BACKGROUND

The correct interpretation of the ECG is pivotal for the accurate diagnosis of many cardiac abnormalities, and conventional computerized interpretation has not been able to reach physician‐level accuracy in detecting (acute) cardiac abnormalities. This study aims to develop and validate a deep neural network for comprehensive automated ECG triage in daily practice.

METHODS AND RESULTS

We developed a 37‐layer convolutional residual deep neural network on a data set of free‐text physician‐annotated 12‐lead ECGs. The deep neural network was trained on a data set with 336.835 recordings from 142.040 patients and validated on an independent validation data set (n=984), annotated by a panel of 5 cardiologists electrophysiologists. The 12‐lead ECGs were acquired in all noncardiology departments of the University Medical Center Utrecht. The algorithm learned to classify these ECGs into the following 4 triage categories: normal, abnormal not acute, subacute, and acute. Discriminative performance is presented with overall and category‐specific concordance statistics, polytomous discrimination indexes, sensitivities, specificities, and positive and negative predictive values. The patients in the validation data set had a mean age of 60.4 years and 54.3% were men. The deep neural network showed excellent overall discrimination with an overall concordance statistic of 0.93 (95% CI, 0.92–0.95) and a polytomous discriminatory index of 0.83 (95% CI, 0.79–0.87).

CONCLUSIONS

This study demonstrates that an end‐to‐end deep neural network can be accurately trained on unstructured free‐text physician annotations and used to consistently triage 12‐lead ECGs. When further fine‐tuned with other clinical outcomes and externally validated in clinical practice, the demonstrated deep learning–based ECG interpretation can potentially improve time to treatment and decrease healthcare burden.

Development of an algorithm for automatic classification of right ventricle deformation patterns in arrhythmogenic right ventricular cardiomyopathy

BACKGROUND

Different disease stages of arrhythmogenic right ventricular cardiomyopathy (ARVC) can be identified by right ventricle (RV) longitudinal deformation (strain) patterns. This requires assessment of the onset of shortening, (systolic) peak strain, and postsystolic index, which is time-consuming and prone to inter- and intra-observer variability. The aim of this study was to design and validate an algorithm to automatically classify RV deformation patterns.

METHODS

We developed an algorithm based on specific local characteristics from the strain curves to detect the parameters required for classification. Determination of the onset of shortening by the algorithm was compared to manual determination by an experienced operator in a dataset containing 186 RV strain curves from 26 subjects carrying a pathogenic plakophilin-2 (PKP2) mutation and 36 healthy subjects. Classification agreement between operator and algorithm was solely based on differences in onset shortening, as the remaining parameters required for classification of RV deformation patterns could be directly obtained from the strain curves.

RESULTS

The median difference between the onset of shortening determined by the experienced operator and by the automatic detector was 5.3 ms [inter-quartile range (IQR) 2.7-8.6 ms]. 96% of the differences were within 1 time frame. Both methods correlated significantly with ρ = 0.97 (P < .001). For 26 PKP2 mutation carriers, there was 100% agreement in classification between the algorithm and experienced operator.

CONCLUSION

The determination of the onset of shortening by the experienced operator was comparable to the algorithm. Our computer algorithm seems a promising method for the automatic classification of RV deformation patterns. The algorithm is publicly available at the MathWorks File Exchange.

3D Myocardial Scar Prediction Model Derived from Multimodality Analysis of Electromechanical Mapping and Magnetic Resonance Imaging

Many cardiac catheter interventions require accurate discrimination between healthy and infarcted myocardia. The gold standard for infarct imaging is late gadolinium-enhanced MRI (LGE-MRI), but during cardiac procedures electroanatomical or electromechanical mapping (EAM or EMM, respectively) is usually employed. We aimed to improve the ability of EMM to identify myocardial infarction by combining multiple EMM parameters in a statistical model. From a porcine infarction model, 3D electromechanical maps were 3D registered to LGE-MRI. A multivariable mixed-effects logistic regression model was fitted to predict the presence of infarct based on EMM parameters. Furthermore, we correlated feature-tracking strain parameters to EMM measures of local mechanical deformation. We registered 787 EMM points from 13 animals to the corresponding MRI locations. The mean registration error was 2.5 ± 1.16 mm. Our model showed a strong ability to predict the presence of infarction (C-statistic = 0.85). Strain parameters were only weakly correlated to EMM measures. The model is accurate in discriminating infarcted from healthy myocardium. Unipolar and bipolar voltages were the strongest predictors.

High-frequency irreversible electroporation for cardiac ablation using an asymmetrical waveform

Background

Irreversible electroporation (IRE) using direct current (DC) is an effective method for the ablation of cardiac tissue. A major drawback of the use of DC-IRE, however, are two problems: requirement of general anesthesia due to severe muscle contractions and the formation of bubbles containing gaseous products from electrolysis. The use of high-frequency alternating current (HF-IRE) is expected to solve both problems, because HF-IRE produces little to no muscle spasms and does not cause electrolysis.

Methods

In the present study, we introduce a novel asymmetric, high-frequency (aHF) waveform for HF-IRE and present the results of a first, small, animal study to test its efficacy.

Results

The data of the experiments suggest that the aHF waveform creates significantly deeper lesions than a symmetric HF waveform of the same energy and frequency (p = 0.003).

Conclusion

We therefore conclude that the use of the aHF enhances the feasibility of the HF-IRE method.

Novel method for electrode-tissue contact measurement with multi-electrode catheters

Aims

With multi-electrode catheters, measuring contact force (CF) on each electrode is technically challenging. Present electrical methods, like the electrical coupling index (ECI) may yield false positive values in pulmonary veins. We developed a novel method that measures electrode-interface resistance (IR) by applying a very local electrical field between neighbouring catheter electrodes while measuring voltage between each catheter electrode and a skin patch. The aim of this study was to evaluate the new IR method to measure electrode-tissue contact.

Methods and results

In vitro, effects of remote high-impedance structures were studied. In addition, both ECI and IR were directly compared with true electrode-tissue CF. In five pigs, the influence of high-impedance pulmonary tissue on ECI and IR was investigated while navigating the free floating catheter into the caval veins. Inside the left atrium (LA), IR was directly compared with CF. Finally, multi-electrode IR measurements in the LA and inferior pulmonary vein (IPV) were compared. In vitro, IR is much less affected by remote high-impedance structures than ECI (3% vs. 32%). Both IR and ECI strongly relate to electrode-tissue CF (r2 = 0.84). In vivo, and in contrast to ECI, IR was not affected by nearby pulmonary tissue. Inside the LA, a strong relation between IR and CF was found. This finding was confirmed by simultaneous multi-electrode measurements in LA and IPV.

Conclusion

Data of the present study suggest that electrode-tissue contact affects the IR while being highly insensitive to remote structures. This method facilitates electrode-tissue contact measurements with circular multi-electrode ablation catheters.

A systematic comparison of cardiovascular magnetic resonance and high resolution histological fibrosis quantification in a chronic porcine infarct model

The noninvasive reference standard for myocardial fibrosis detection on cardiovascular magnetic resonance imaging (CMR) is late gadolinium enhancement (LGE). Currently there is no consensus on the preferred method for LGE quantification. Moreover myocardial wall thickening (WT) and strain are measures of regional deformation and function. The aim of this research was to systematically compare in vivo CMR parameters, such as LGE, WT and strain, with histological fibrosis quantification. Eight weeks after 90 min ischemia/reperfusion of the LAD artery, 16 pigs underwent in vivo Cine and LGE CMR. Histological sections from transverse heart slices were digitally analysed for fibrosis quantification. Mean fibrosis percentage of analysed sections was related to the different CMR techniques (using segmentation or feature tracking software) for each slice using a linear mixed model analysis. The full width at half maximum (FWHM) technique for quantification of LGE yielded the highest R2 of 60%. Cine derived myocardial WT explained 16-36% of the histological myocardial fibrosis. The peak circumferential and radial strain measured by feature tracking could explain 15 and 10% of the variance of myocardial fibrosis, respectively. The used method to systematically compare CMR image data with digital histological images is novel and feasible. Myocardial WT and strain were only modestly related with the amount of fibrosis. The fully automatic FWHM analysis technique is the preferred method to detect myocardial fibrosis.

Acute and Long-Term Effects of Full-Power Electroporation Ablation Directly on the Porcine Esophagus

Background—

Esophageal ulceration and fistula are complications of pulmonary vein isolation using thermal energy sources. Irreversible electroporation is a novel, nonthermal ablation modality for pulmonary vein isolation. A single 200 J application can create deep myocardial lesions. Acute and chronic effects of this new energy source on the esophagus are unknown.

Methods and Results—

In 8 pigs (±70 kg), the suprasternal esophagus was surgically exposed. A linear suction device with a single 35-mm long and 6-mm wide protruding linear electrode inside a plastic suction cup was used for ablation. Single, nonarcing, nonbarotraumatic, cathodal 100 and 200 J applications were delivered at 2 different sites on the anterior esophageal adventitia. No proton-pump inhibitors were administered during follow-up. Esophagoscopy was performed at days 2 and 7. After euthanasia at day 60, the esophagus was evaluated visually and histologically. All ablations were uneventful. Esophagoscopy at day 2 showed small white densities in the ablated areas, which appeared to be small intraepithelial vesicles. No epithelial erythema, erosions, or ulcerations were seen. At day 7, all densities had disappeared, and all esophaguses appeared completely normalized. After euthanasia, there were no macroscopically visible lesions on the adventitia or epithelium. Histologically, a small scar was observed at the outer part of the muscular layer, whereas the mucosa and submucosa were normal.

Conclusions—

Esophageal architecture remains unaffected 2 months after irreversible electroporation, purposely targeting the adventitia. Irreversible electroporation seems to be a safe modality for catheter ablation near the esophagus.

Myocardial Lesion Size After Epicardial Electroporation Catheter Ablation After Subxiphoid Puncture

Background—

Irreversible electroporation is a promising nonthermal ablation modality able to create deep myocardial lesions. We investigated lesion size after epicardial electroporation catheter ablation with various energy levels after subxiphoid pericardial puncture.

Methods and Results—

In six 6-month-old pigs (60–75 kg), a custom deflectable octopolar 12-mm circular catheter with 2-mm ring electrodes was introduced via a deflectable sheath after pericardial access by subxiphoid puncture. Nonarcing, nonbarotraumatic, cathodal 50, 100, and 200 J electroporation applications were delivered randomly on the basal, mid and lateral left ventricle. After 3-month survival, myocardial lesion size and degree of intimal hyperplasia of the coronary arteries were analyzed histologically. Five animals survived the follow-up without complications and 1 animal died of shock after the subxiphoid puncture. At autopsy, whitish circular scars with indentation of the epicardium could be identified. Average lesion depths of the 50-, 100-, and 200-J lesions were 5.0±2.1, 7.0±2.0, and 11.9±1.5 mm, respectively. Average lesion widths of the 50-, 100-, and 200-J lesions were 16.6±1.1, 16.2±4.3, and 19.8±1.8 mm, respectively. In the 100- and 200-J cross sections, transmural left ventricular lesions and significant tissue shrinkage were observed. No intimal hyperplasia of the coronary arteries was observed.

Conclusions—

Epicardial electroporation ablation after subxiphoid pericardial puncture can create deep, wide, and transmural ventricular myocardial lesions. There is a significant relationship between the amounts of electroporation energy delivered epicardially and lesion size in the absence of major adverse events.

High resolution systematic digital histological quantification of cardiac fibrosis and adipose tissue in phospholamban p.Arg14del mutation associated cardiomyopathy

Myocardial fibrosis can lead to heart failure and act as a substrate for cardiac arrhythmias. In dilated cardiomyopathy diffuse interstitial reactive fibrosis can be observed, whereas arrhythmogenic cardiomyopathy is characterized by fibrofatty replacement in predominantly the right ventricle. The p.Arg14del mutation in the phospholamban (PLN) gene has been associated with dilated cardiomyopathy and recently also with arrhythmogenic cardiomyopathy. Aim of the present study is to determine the exact pattern of fibrosis and fatty replacement in PLN p.Arg14del mutation positive patients, with a novel method for high resolution systematic digital histological quantification of fibrosis and fatty tissue in cardiac tissue. Transversal mid-ventricular slices (n = 8) from whole hearts were collected from patients with the PLN p.Arg14del mutation (age 48±16 years; 4 (50%) male). An in-house developed open source MATLAB script was used for digital analysis of Masson's trichrome stained slides (http://sourceforge.net/projects/fibroquant/). Slides were divided into trabecular, inner and outer compact myocardium. Per region the percentage of connective tissue, cardiomyocytes and fatty tissue was quantified. In PLN p.Arg14del mutation associated cardiomyopathy, myocardial fibrosis is predominantly present in the left posterolateral wall and to a lesser extent in the right ventricular wall, whereas fatty changes are more pronounced in the right ventricular wall. No difference in distribution pattern of fibrosis and adipocytes was observed between patients with a clinical predominantly dilated and arrhythmogenic cardiomyopathy phenotype. In the future, this novel method for quantifying fibrosis and fatty tissue can be used to assess cardiac fibrosis and fatty tissue in animal models and a broad range of human cardiomyopathies.