Utilization of and perceived need for simulators in clinical electrophysiology: results from an EHRA physician survey.

AIMS: Simulator training has been recently introduced in electrophysiology (EP) programmes in order to improve catheter manipulation skills without complication risks. The aim of this study is to survey the current use of EP simulators and the perceived need for these tools in clinical training and practice. METHODS AND RESULTS: A 20-item online questionnaire developed by the Scientific Initiatives Committee of the European Heart Rhythm Association (EHRA) in collaboration with EHRA Digital Committee was disseminated through the EHRA Scientific Research Network members, national EP groups, and social media platforms. Seventy-four respondents from 22 countries (73% males; 50% under 40 years old) completed the survey. Despite being perceived as useful among EP professionals (81%), EP simulators are rarely a part of the institutional cardiology training programme (20%) and only 18% of the respondents have an EP simulator at their institution. When available, simulators are mainly used in EP to train transseptal puncture, ablation, and mapping, followed by device implantation (cardiac resynchronization therapy [CRT], leadless, and conduction system pacing [CSP]). Almost all respondents (96%) believe that simulator programmes should be a part of the routine institutional EP training, hopefully developed by EHRA, in order to improve the efficacy and safety of EP procedures and in particular CSP 58%, CRT 42%, leadless pacing 38%, or complex arrhythmia ablations (VT 58%, PVI 45%, and PVC 42%). CONCLUSION: This current EHRA survey identified a perceived need but a lack of institutional simulator programme access for electrophysiologists who could benefit from it in order to speed up the learning curve process and reduce complications of complex EP procedures.

Trends in adoption of extravascular cardiac implantable electronic devices: the Dutch cohort.

INTRODUCTION: Conventional implantable cardioverter-defibrillators (ICDs) and pacemakers carry a risk of pocket- and lead-related complications in particular. To avoid these complications, extravascular devices (EVDs) have been developed, such as the subcutaneous ICD (S-ICD) and leadless pacemaker (LP). However, data on patient or centre characteristics related to the actual adoption of EVDs are lacking. OBJECTIVE: To assess real-world nationwide trends in EVD adoption in the Netherlands. METHODS: Using the Netherlands Heart Registration, all consecutive patients with a de novo S­ICD or conventional single-chamber ICD implantation between 2012-2020, or de novo LP or conventional single-chamber pacemaker implantation between 2014-2020 were included. Trends in adoption are described for various patient and centre characteristics. RESULT: From 2012-2020, 2190 S­ICDs and 10,683 conventional ICDs were implanted; from 2014-2020, 712 LPs and 11,103 conventional pacemakers were implanted. The general use has increased (S-ICDs 8 to 21%; LPs 1 to 8%), but this increase seems to have reached a plateau. S­ICD recipients were younger than conventional ICD recipients (p < 0.001) and more often female (p < 0.001); LP recipients were younger than conventional pacemaker recipients (p < 0.001) and more often male (p = 0.03). Both S­ICDs and LPs were mainly implanted in high-volume centres with cardiothoracic surgery on-site, although over time S­ICDs were increasingly implanted in centres without cardiothoracic surgery (p < 0.001). CONCLUSION: This nationwide study demonstrated a relatively quick adoption of innovative EVDs with a plateau after approximately 4 years. S­ICD use is especially high in younger patients. EVDs are mainly implanted in high-volume centres with cardiothoracic surgery back-up, but S­ICD use is expanding beyond those centres.

Multimodal explainable artificial intelligence identifies patients with non-ischaemic cardiomyopathy at risk of lethal ventricular arrhythmias.

The efficacy of an implantable cardioverter-defibrillator (ICD) in patients with a non-ischaemic cardiomyopathy for primary prevention of sudden cardiac death is increasingly debated. We developed a multimodal deep learning model for arrhythmic risk prediction that integrated late gadolinium enhanced (LGE) cardiac magnetic resonance imaging (MRI), electrocardiography (ECG) and clinical data. Short-axis LGE-MRI scans and 12-lead ECGs were retrospectively collected from a cohort of 289 patients prior to ICD implantation, across two tertiary hospitals. A residual variational autoencoder was developed to extract physiological features from LGE-MRI and ECG, and used as inputs for a machine learning model (DEEP RISK) to predict malignant ventricular arrhythmia onset. In the validation cohort, the multimodal DEEP RISK model predicted malignant ventricular arrhythmias with an area under the receiver operating characteristic curve (AUROC) of 0.84 (95% confidence interval (CI) 0.71-0.96), a sensitivity of 0.98 (95% CI 0.75-1.00) and a specificity of 0.73 (95% CI 0.58-0.97). The models trained on individual modalities exhibited lower AUROC values compared to DEEP RISK [MRI branch: 0.80 (95% CI 0.65-0.94), ECG branch: 0.54 (95% CI 0.26-0.82), Clinical branch: 0.64 (95% CI 0.39-0.87)]. These results suggest that a multimodal model achieves high prognostic accuracy in predicting ventricular arrhythmias in a cohort of patients with non-ischaemic systolic heart failure, using data collected prior to ICD implantation.

Novel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset.

Background: Segmenting computed tomography (CT) is crucial in various clinical applications, such as tailoring personalized cardiac ablation for managing cardiac arrhythmias. Automating segmentation through machine learning (ML) is hindered by the necessity for large, labeled training data, which can be challenging to obtain. This article proposes a novel approach for automated, robust labeling using domain knowledge to achieve high-performance segmentation by ML from a small training set. The approach, the domain knowledge-encoding (DOKEN) algorithm, reduces the reliance on large training datasets by encoding cardiac geometry while automatically labeling the training set. The method was validated in a hold-out dataset of CT results from an atrial fibrillation (AF) ablation study. Methods: The DOKEN algorithm parses left atrial (LA) structures, extracts "anatomical knowledge" by leveraging digital LA models (available publicly), and then applies this knowledge to achieve high ML segmentation performance with a small number of training samples. The DOKEN-labeled training set was used to train a nnU-Net deep neural network (DNN) model for segmenting cardiac CT in N = 20 patients. Subsequently, the method was tested in a hold-out set with N = 100 patients (five times larger than training set) who underwent AF ablation. Results: The DOKEN algorithm integrated with the nn-Unet model achieved high segmentation performance with few training samples, with a training to test ratio of 1:5. The Dice score of the DOKEN-enhanced model was 96.7% (IQR: 95.3% to 97.7%), with a median error in surface distance of boundaries of 1.51 mm (IQR: 0.72 to 3.12) and a mean centroid-boundary distance of 1.16 mm (95% CI: -4.57 to 6.89), similar to expert results (r = 0.99; p < 0.001). In digital hearts, the novel DOKEN approach segmented the LA structures with a mean difference for the centroid-boundary distances of -0.27 mm (95% CI: -3.87 to 3.33; r = 0.99; p < 0.0001). Conclusions: The proposed novel domain knowledge-encoding algorithm was able to perform the segmentation of six substructures of the LA, reducing the need for large training data sets. The combination of domain knowledge encoding and a machine learning approach could reduce the dependence of ML on large training datasets and could potentially be applied to AF ablation procedures and extended in the future to other imaging, 3D printing, and data science applications.

Dynamic prediction of malignant ventricular arrhythmias using neural networks in patients with an implantable cardioverter-defibrillator.

BACKGROUND: Risk stratification for ventricular arrhythmias currently relies on static measurements that fail to adequately capture dynamic interactions between arrhythmic substrate and triggers over time. We trained and internally validated a dynamic machine learning (ML) model and neural network that extracted features from longitudinally collected electrocardiograms (ECG), and used these to predict the risk of malignant ventricular arrhythmias. METHODS: A multicentre study in patients implanted with an implantable cardioverter-defibrillator (ICD) between 2007 and 2021 in two academic hospitals was performed. Variational autoencoders (VAEs), which combine neural networks with variational inference principles, and can learn patterns and structure in data without explicit labelling, were trained to encode the mean ECG waveforms from the limb leads into 16 variables. Supervised dynamic ML models using these latent ECG representations and clinical baseline information were trained to predict malignant ventricular arrhythmias treated by the ICD. Model performance was evaluated on a hold-out set, using time-dependent receiver operating characteristic (ROC) and calibration curves. FINDINGS: 2942 patients (61.7 ± 13.9 years, 25.5% female) were included, with a total of 32,129 ECG recordings during a mean follow-up of 43.9 ± 35.9 months. The mean time-varying area under the ROC curve for the dynamic model was 0.738 ± 0.07, compared to 0.639 ± 0.03 for a static (i.e. baseline-only model). Feature analyses indicated dynamic changes in latent ECG representations, particularly those affecting the T-wave morphology, were of highest importance for model predictions. INTERPRETATION: Dynamic ML models and neural networks effectively leverage routinely collected longitudinal ECG recordings for personalised and updated predictions of malignant ventricular arrhythmias, outperforming static models. FUNDING: This publication is part of the project DEEP RISK ICD (with project number 452019308) of the research programme Rubicon which is (partly) financed by the Dutch Research Council (NWO). This research is partly funded by the Amsterdam Cardiovascular Sciences (personal grant F.V.Y.T).