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).

Optimizing patient selection for primary prevention implantable cardioverter-defibrillator implantation: utilizing multimodal machine learning to assess risk of implantable cardioverter-defibrillator non-benefit.

AIMS: Left ventricular ejection fraction (LVEF) is suboptimal as a sole marker for predicting sudden cardiac death (SCD). Machine learning (ML) provides new opportunities for personalized predictions using complex, multimodal data. This study aimed to determine if risk stratification for implantable cardioverter-defibrillator (ICD) implantation can be improved by ML models that combine clinical variables with 12-lead electrocardiograms (ECG) time-series features. METHODS AND RESULTS: A multicentre study of 1010 patients (64.9 ± 10.8 years, 26.8% female) with ischaemic, dilated, or non-ischaemic cardiomyopathy, and LVEF ≤ 35% implanted with an ICD between 2007 and 2021 for primary prevention of SCD in two academic hospitals was performed. For each patient, a raw 12-lead, 10-s ECG was obtained within 90 days before ICD implantation, and clinical details were collected. Supervised ML models were trained and validated on a development cohort (n = 550) from Hospital A to predict ICD non-arrhythmic mortality at three-year follow-up (i.e. mortality without prior appropriate ICD-therapy). Model performance was evaluated on an external patient cohort from Hospital B (n = 460). At three-year follow-up, 16.0% of patients had died, with 72.8% meeting criteria for non-arrhythmic mortality. Extreme gradient boosting models identified patients with non-arrhythmic mortality with an area under the receiver operating characteristic curve (AUROC) of 0.90 [95% confidence intervals (CI) 0.80-1.00] during internal validation. In the external cohort, the AUROC was 0.79 (95% CI 0.75-0.84). CONCLUSIONS: ML models combining ECG time-series features and clinical variables were able to predict non-arrhythmic mortality within three years after device implantation in a primary prevention population, with robust performance in an independent cohort.

Machine learning of electrophysiological signals for the prediction of ventricular arrhythmias: systematic review and examination of heterogeneity between studies.

BACKGROUND: Ventricular arrhythmia (VA) precipitating sudden cardiac arrest (SCD) is among the most frequent causes of death and pose a high burden on public health systems worldwide. The increasing availability of electrophysiological signals collected through conventional methods (e.g. electrocardiography (ECG)) and digital health technologies (e.g. wearable devices) in combination with novel predictive analytics using machine learning (ML) and deep learning (DL) hold potential for personalised predictions of arrhythmic events. METHODS: This systematic review and exploratory meta-analysis assesses the state-of-the-art of ML/DL models of electrophysiological signals for personalised prediction of malignant VA or SCD, and studies potential causes of bias (PROSPERO, reference: CRD42021283464). Five electronic databases were searched to identify eligible studies. Pooled estimates of the diagnostic odds ratio (DOR) and summary area under the curve (AUROC) were calculated. Meta-analyses were performed separately for studies using publicly available, ad-hoc datasets, versus targeted clinical data acquisition. Studies were scored on risk of bias by the PROBAST tool. FINDINGS: 2194 studies were identified of which 46 were included in the systematic review and 32 in the meta-analysis. Pooling of individual models demonstrated a summary AUROC of 0.856 (95% CI 0.755-0.909) for short-term (time-to-event up to 72 h) prediction and AUROC of 0.876 (95% CI 0.642-0.980) for long-term prediction (time-to-event up to years). While models developed on ad-hoc sets had higher pooled performance (AUROC 0.919, 95% CI 0.867-0.952), they had a high risk of bias related to the re-use and overlap of small ad-hoc datasets, choices of ML tool and a lack of external model validation. INTERPRETATION: ML and DL models appear to accurately predict malignant VA and SCD. However, wide heterogeneity between studies, in part due to small ad-hoc datasets and choice of ML model, may reduce the ability to generalise and should be addressed in future studies. 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).

Reduction in long-term mortality using remote device monitoring in a large real-world population of patients with implantable defibrillators.

AIMS: Remote monitoring (RM) for implantable cardioverter-defibrillators (ICDs) is advocated for the potential of early detection of disease progression and device dysfunction. While studies have examined the effect of RM on clinical outcomes in carefully selected populations of heart failure patients implanted with ICDs from a single vendor, there is a paucity of data in real-world patients. We aimed to assess the long-term effect of RM in a representative ICD population using real-world data. METHODS AND RESULTS: This is an observational retrospective longitudinal study of 1004 patients implanted with an ICD or cardiac resynchronization therapy device (CRT-D) from all device vendors between 2010 and 2021. Patients started on RM (N = 403) within 90 days following de novo device implantation and yearly in-office visits were compared with patients with only bi-yearly in-office follow-up (non-RM, N = 601). In a propensity score matched cohort of 430 patients (mean age 61.4 ± 14.3 years, 26.7% female), all-cause mortality at 4-year was 12.6% in the RM and 27.7% in the non-RM group [hazard ratio (HR) 0.52, 95% confidence interval (CI) 0.32-0.82; P = 0.005]. No difference in inappropriate ICD-therapy (HR 1.90, 95% CI 0.86-4.21; P = 0.122) was observed. The risk of appropriate ICD-therapy (HR 1.71, 95% CI 1.07-2.74; P = 0.026) was higher in the RM group. CONCLUSION: Remote monitoring was associated with a reduction in long-term all-cause and cardiac mortality compared with traditional office visits in a real-world ICD population.

Accelerometer-assessed physical behavior and the association with clinical outcomes in implantable cardioverter-defibrillator recipients: A systematic review.

Background: Current implantable cardioverter-defibrillator (ICD) devices are equipped with a device-embedded accelerometer capable of capturing physical activity (PA). In contrast, wearable accelerometer-based methods enable the measurement of physical behavior (PB) that encompasses not only PA but also sleep behavior, sedentary time, and rest-activity patterns. Objective: This systematic review evaluates accelerometer-based methods used in patients carrying an ICD or at high risk of sudden cardiac death. Methods: Papers were identified via the OVID MEDLINE and OVID EMBASE databases. PB could be assessed using a wearable accelerometer or an embedded accelerometer in the ICD. Results: A total of 52 papers were deemed appropriate for this review. Out of these studies, 30 examined device-embedded accelerometry (189,811 patients), 19 examined wearable accelerometry (1601 patients), and 3 validated wearable accelerometry against device-embedded accelerometry (106 patients). The main findings were that a low level of PA after implantation of the ICD and a decline in PA were both associated with an increased risk of mortality, heart failure hospitalization, and appropriate ICD shock. Second, PA was affected by cardiac factors (eg, onset of atrial fibrillation, ICD shocks) and noncardiac factors (eg, seasonal differences, societal factors). Conclusion: This review demonstrated the potential of accelerometer-measured PA as a marker of clinical deterioration and ventricular arrhythmias. Notwithstanding that the evidence of PB assessed using wearable accelerometry was limited, there seems to be potential for accelerometers to improve early warning systems and facilitate preventative and proactive strategies.

Rationale and design of the SafeHeart study: Development and testing of a mHealth tool for the prediction of arrhythmic events and implantable cardioverter-defibrillator therapy.

Background: Patients with an implantable cardioverter-defibrillator (ICD) are at a high risk of malignant ventricular arrhythmias. The use of remote ICD monitoring, wearable devices, and patient-reported outcomes generate large volumes of potential valuable data. Artificial intelligence-based methods can be used to develop personalized prediction models and improve early-warning systems. Objective: The purpose of this study was to develop an integrated web-based personalized prediction engine for ICD therapy. Methods: This international, multicenter, prospective, observational study consists of 2 phases: (1) a development study and (2) a feasibility study. We plan to enroll 400 participants with an ICD (with or without cardiac resynchronization therapy) on remote monitoring: 300 participants in the development study and 100 in the feasibility study. During 12-month follow-up, electronic health record data, remote monitoring data, accelerometry-assessed physical behavior data, and patient-reported data are collected. By using machine- and deep-learning approaches, a prediction engine is developed to assess the risk probability of ICD therapy (shock and antitachycardia pacing). The feasibility of the prediction engine as a clinical tool, the SafeHeart Platform, is assessed during the feasibility study. Results: Development study recruitment commenced in 2021. The feasibility study starts in 2022. Conclusion: SafeHeart is the first study to prospectively collect a multimodal data set to construct a personalized prediction engine for ICD therapy. Moreover, SafeHeart explores the integration and added value of detailed objective accelerometer data in the prediction of clinical events. The translation of the SafeHeart Platform to clinical practice is examined during the feasibility study.

Patient-reported outcomes in symptom-driven remote arrhythmia monitoring: evaluation of the Dutch HartWacht-telemonitoring programme.

Aims: There is limited quantitative evidence on the effect of symptom-driven telemonitoring for cardiac arrhythmias on patient-reported outcomes. We evaluated the effect of a symptom-driven remote arrhythmia monitoring programme on the patient-reported health-related quality of life (HRQoL), sense of safety, physical limitations, and self-management. Methods and results: This was an observational retrospective longitudinal study of the symptom-driven HartWacht-telemonitoring programme using a remote single-lead electrocardiogram monitoring system. Real-world patient data from participants who were enrolled in the telemonitoring programme for (suspected) symptomatic atrial fibrillation (AF) between July 2017 and September 2019 were evaluated. Primary outcomes were the patient-reported generic HRQoL, disease-specific HRQoL, sense of safety, physical limitations, and self-management at date of enrolment, 3 months and 6 months of follow-up. Outcomes were compared to a historical control group consisting of AF patients receiving standard care. A total of 109 participants in the HartWacht programme [59 men (54%); mean age 61 ± 11 years; 72% diagnosed AF] were included in complete case analysis. There was no significant change in HRQoL and sense of safety during follow-up. A significant improvement in the perceived physical limitations was observed. The level of self-management declined significantly during follow-up. Comparisons to the historic control group (n = 83) showed no difference between the patient-reported disease-specific HRQoL, sense of safety and physical limitations at 6 months of follow-up. Conclusion: Symptom-driven remote arrhythmia monitoring for AF does not seem to affect HRQoL and sense of safety, whereas the perceived physical limitations tend to improve. Patient-reported self-management declined during the first 6 months of participation.

Predictors and outcomes of procedural failure of percutaneous coronary intervention of a chronic total occlusion-A subanalysis of the EXPLORE trial.

OBJECTIVE: To evaluate predictors of procedural success of percutaneous coronary intervention (PCI) of chronic total coronary occlusions (CTOs) in a non-infarct-related artery following ST-segment elevation myocardial infarction (STEMI), and demonstrate the effect on left ventricular functionality (LVF), infarct size (IS), and pro-arrhythmic electrocardiogram (ECG) parameters. BACKGROUND: Predictors of unsuccessful revascularization of a CTO are numerous, although following STEMI, these are lacking. Besides, effects of failed CTO PCI (FPCI) on the myocardium are unknown. METHODS: This is a subanalysis of the EXPLORE trial, in which 302 STEMI patients with a concurrent CTO were randomized to CTO PCI (n = 147) or no-CTO PCI (NPCI, n = 154). For the purpose of this subanalysis, we divided patients into successful CTO PCI (SPCI, n = 106), FPCI (n = 41), and NPCI (n = 154) groups. Cardiac magnetic resonance imaging and angiographic data were derived from the EXPLORE database, combined with ECG parameters. To gain more insight, all outcomes were compared with patients that did not undergo CTO PCI. RESULTS: In multivariate regression, only CTO lesion length >20 mm was an independent predictor of procedural failure (OR 3.31 [1.49-7.39]). No significant differences in median left ventricular ejection fraction, left ventricular end-diastolic volume, IS, and the pro-arrhythmic ECG parameters such as QT-dispersion, QTc-time, and TpTe-intervals were seen between the SPCI and FPCI groups at 4 months follow-up. CONCLUSION: This subanalysis of the EXPLORE trial has demonstrated that a CTO lesion length >20 mm is an independent predictor of CTO PCI failure, whereas procedural failure did not lead to any adverse effects on LVF nor pro-arrhythmic ECG parameters.

The effect of revascularization of a chronic total coronary occlusion on electrocardiographic variables. A sub-study of the EXPLORE trial.

INTRODUCTION: Chronic total coronary occlusions (CTOs) have been associated with a higher prevalence of ventricular arrhythmias compared to patients without a CTO. We evaluated the effect of CTO revascularization on electrocardiographic (ECG) variables. METHODS: We studied a selection of ST-elevation myocardial infarction patients with a concomitant CTO enrolled in the EXPLORE trial. ECG variables and cardiac function were analysed at baseline and at 4 months follow-up. RESULTS: Patients were randomized to percutaneous coronary intervention (PCI) of their CTO (n = 77) or to no-CTO PCI (n = 81). At follow-up, median QT dispersion was significantly lower in the CTO PCI group compared to the no-CTO PCI group (46 ms [33-58] vs. 54 ms [37-68], P = 0.043). No independent association was observed between ECG variables and cardiac function. CONCLUSION: Revascularization of a CTO after STEMI significantly shortened QT dispersion at 4 months follow-up. These findings support the hypothesis that CTO revascularization reduces the pro-arrhythmic substrate in CTO patients.