Artificial intelligence-enhanced electrocardiography derived body mass index as a predictor of future cardiometabolic disease.

The electrocardiogram (ECG) can capture obesity-related cardiac changes. Artificial intelligence-enhanced ECG (AI-ECG) can identify subclinical disease. We trained an AI-ECG model to predict body mass index (BMI) from the ECG alone. Developed from 512,950 12-lead ECGs from the Beth Israel Deaconess Medical Center (BIDMC), a secondary care cohort, and validated on UK Biobank (UKB) (n = 42,386), the model achieved a Pearson correlation coefficient (r) of 0.65 and 0.62, and an R2 of 0.43 and 0.39 in the BIDMC cohort and UK Biobank, respectively for AI-ECG BMI vs. measured BMI. We found delta-BMI, the difference between measured BMI and AI-ECG-predicted BMI (AI-ECG-BMI), to be a biomarker of cardiometabolic health. The top tertile of delta-BMI showed increased risk of future cardiometabolic disease (BIDMC: HR 1.15, p < 0.001; UKB: HR 1.58, p < 0.001) and diabetes mellitus (BIDMC: HR 1.25, p < 0.001; UKB: HR 2.28, p < 0.001) after adjusting for covariates including measured BMI. Significant enhancements in model fit, reclassification and improvements in discriminatory power were observed with the inclusion of delta-BMI in both cohorts. Phenotypic profiling highlighted associations between delta-BMI and cardiometabolic diseases, anthropometric measures of truncal obesity, and pericardial fat mass. Metabolic and proteomic profiling associates delta-BMI positively with valine, lipids in small HDL, syntaxin-3, and carnosine dipeptidase 1, and inversely with glutamine, glycine, colipase, and adiponectin. A genome-wide association study revealed associations with regulators of cardiovascular/metabolic traits, including SCN10A, SCN5A, EXOG and RXRG. In summary, our AI-ECG-BMI model accurately predicts BMI and introduces delta-BMI as a non-invasive biomarker for cardiometabolic risk stratification.

Bariatric surgery partially reverses subclinical proarrhythmic structural, electrophysiological and autonomic changes in obesity.

BACKGROUND: Obesity confers higher risks of cardiac arrhythmias. The extent to which weight loss reverses subclinical proarrhythmic adaptations in arrhythmia-free obese individuals is unknown. OBJECTIVE: To study structural, electrophysiological and autonomic remodelling in arrhythmia-free obese patients, and their reversibility with bariatric surgery using electrocardiographic imaging (ECGi). METHODS: Sixteen arrhythmia-free obese patients (43+12years, 13 female, BMI 46.7+5.5kg/m2) had ECGi pre-bariatric surgery (PreSurg), of which twelve had ECGi post-surgery (PostSurg, 36.8+6.5kg/m2). Sixteen age- and sex-matched lean healthy individuals (42+11 years, BMI 22.8+2.6kg/m2) acted as controls and had ECGi once. RESULTS: Obesity was associated with structural (increased epicardial fat volumes and left ventricular mass), autonomic (blunted heart rate variability) and electrophysiological (slower atrial conduction and steeper ventricular repolarisation gradients) remodelling. Following bariatric surgery, there was partial structural reverse remodelling, with a reduction in epicardial fat volumes (68.7cm3 vs 64.5cm3, p=0.0010) and left ventricular mass (33g/m2.7 vs 25g/m2.7, p<0.0005). There was also partial electrophysiological reverse remodelling with a reduction in mean spatial ventricular repolarisation gradients (26mm/ms vs 19mm/ms, p=0.0009), although atrial activation remained prolonged. Heart rate variability, quantified by standard deviation of successive differences of RR intervals, was also partially improved following bariatric surgery (18.7ms vs 25.9ms, p=0.017). Computational modelling showed PreSurg obese hearts had a greater window of vulnerability to unidirectional block and had earlier spiral-wave break-up with more complex re-entry patterns than PostSurg counterparts. CONCLUSION: Obesity is associated with adverse electrophysiological, structural and autonomic remodelling that is partially reversed after bariatric surgery. These data have important implications for bariatric surgery weight thresholds and weight loss strategies.

The Spatial Ventricular Gradient Is Associated With Inducibility of Ventricular Arrhythmias During Electrophysiology Study.

BACKGROUND: Myocardial electrical heterogeneity is critical for normal cardiac electromechanical function, but abnormal or excessive electrical heterogeneity is proarrhythmic. The spatial ventricular gradient (SVG), a vectorcardiographic measure of electrical heterogeneity, has been associated with arrhythmic events during long-term follow-up, but its relationship with short-term inducibility of ventricular arrhythmias (VAs) is unclear. OBJECTIVE: This study was designed to determine associations between SVG and inducible VAs during electrophysiology study. METHODS: A retrospective study was conducted of adults without prior sustained VA, cardiac arrest, or implantable cardioverter-defibrillator who underwent ventricular stimulation for evaluation of syncope and nonsustained ventricular tachycardia or for risk stratification before primary prevention implantable cardioverter-defibrillator implantation. The 12-lead electrocardiograms were converted into vectorcardiograms, and SVG magnitude (SVGmag) and direction (azimuth and elevation) were calculated. Odds of inducible VA were regressed by logistic models. RESULTS: Of 143 patients (median age, 69 years; 80% male; median left ventricular ejection fraction [LVEF], 47%; 52% myocardial infarction), 34 (23.8%) had inducible VAs. Inducible patients had lower median LVEF (38% vs 50%; P < .0001), smaller SVGmag (29.5 vs 39.4 mV·ms; P = .0099), and smaller cosine SVG azimuth (cosSVGaz; 0.64 vs 0.89; P = .0007). When LVEF, SVGmag, and cosSVGaz were dichotomized at their medians, there was a 39-fold increase in adjusted odds (P = .002) between patients with all low LVEF, SVGmag, and cosSVGaz (65% inducible) compared with patients with all high LVEF, SVGmag, and cosSVGaz (4% [n = 1] inducible). After multivariable adjustment, SVGmag, cosSVGaz, and sex but not LVEF or other characteristics remained associated with inducible VAs. CONCLUSION: Assessment of electrical heterogeneity by SVG, which reflects abnormal electrophysiologic substrate, adds to LVEF and identifies patients at high and low risk of inducible VA at electrophysiology study.

Machine learning-derived cycle length variability metrics predict spontaneously terminating ventricular tachycardia in implantable cardioverter defibrillator recipients.

Aims: Implantable cardioverter defibrillator (ICD) therapies have been associated with increased mortality and should be minimized when safe to do so. We hypothesized that machine learning-derived ventricular tachycardia (VT) cycle length (CL) variability metrics could be used to discriminate between sustained and spontaneously terminating VT. Methods and results: In this single-centre retrospective study, we analysed data from 69 VT episodes stored on ICDs from 27 patients (36 spontaneously terminating VT, 33 sustained VT). Several VT CL parameters including heart rate variability metrics were calculated. Additionally, a first order auto-regression model was fitted using the first 10 CLs. Using features derived from the first 10 CLs, a random forest classifier was used to predict VT termination. Sustained VT episodes had more stable CLs. Using data from the first 10 CLs only, there was greater CL variability in the spontaneously terminating episodes (mean of standard deviation of first 10 CLs: 20.1 ± 8.9 vs. 11.5 ± 7.8 ms, P < 0.0001). The auto-regression coefficient was significantly greater in spontaneously terminating episodes (mean auto-regression coefficient 0.39 ± 0.32 vs. 0.14 ± 0.39, P < 0.005). A random forest classifier with six features yielded an accuracy of 0.77 (95% confidence interval 0.67 to 0.87) for prediction of VT termination. Conclusion: Ventricular tachycardia CL variability and instability are associated with spontaneously terminating VT and can be used to predict spontaneous VT termination. Given the harmful effects of unnecessary ICD shocks, this machine learning model could be incorporated into ICD algorithms to defer therapies for episodes of VT that are likely to self-terminate.

Information theory-based direct causality measure to assess cardiac fibrillation dynamics.

Understanding the mechanism sustaining cardiac fibrillation can facilitate the personalization of treatment. Granger causality analysis can be used to determine the existence of a hierarchical fibrillation mechanism that is more amenable to ablation treatment in cardiac time-series data. Conventional Granger causality based on linear predictability may fail if the assumption is not met or given sparsely sampled, high-dimensional data. More recently developed information theory-based causality measures could potentially provide a more accurate estimate of the nonlinear coupling. However, despite their successful application to linear and nonlinear physical systems, their use is not known in the clinical field. Partial mutual information from mixed embedding (PMIME) was implemented to identify the direct coupling of cardiac electrophysiology signals. We show that PMIME requires less data and is more robust to extrinsic confounding factors. The algorithms were then extended for efficient characterization of fibrillation organization and hierarchy using clinical high-dimensional data. We show that PMIME network measures correlate well with the spatio-temporal organization of fibrillation and demonstrated that hierarchical type of fibrillation and drivers could be identified in a subset of ventricular fibrillation patients, such that regions of high hierarchy are associated with high dominant frequency.

Limits of the spatial ventricular gradient and QRST angles in patients with normal electrocardiograms and no known cardiovascular disease stratified by age, sex, and race.

INTRODUCTION: Measurement of the spatial ventricular gradient (SVG), spatial QRST angles, and other vectorcardiographic measures of myocardial electrical heterogeneity have emerged as novel risk stratification methods for sudden cardiac death and other adverse cardiovascular events. Prior studies of normal limits of these measurements included primarily young, healthy, White volunteers, but normal limits in older patients are unknown. The influence of race and body mass index (BMI) on these measurements is also unclear. METHODS: Normal 12-lead electrocardiograms (ECGs) from a single center were identified. Patients with abnormal cardiovascular, pulmonary, or renal history (assessed by International Classification of Disease [ICD-9/ICD-10] codes) or abnormal cardiovascular imaging were excluded. The SVG and QRST angles were measured and stratified by age, sex, and race. Multivariable linear regression was used to assess the influence of age, BMI, and heart rate (HR) on these measurements. RESULTS: Among 3292 patients, observed ranges of SVG and QRST angles (peak and mean) differed significantly based on sex, age, and race. Sex differences attenuated with increasing age. Men tended to have larger SVG magnitude (60.4 [46.1-77.8] vs. 52.5 [41.3-65.8] mv*ms, p < .0001) and elevation, and more anterior/negative SVG azimuth (-14.8 [-25.1 to -4.3] vs. 1.3 [-9.8 to 10.5] deg, p < .0001) compared to women. Men also had wider QRST angles. Observed ranges varied significantly with BMI and HR. SVG and QRST angle measurements were robust to different filtering bandwidths and moderate fiducial point annotation errors, but were heavily affected by changes in baseline correction. CONCLUSIONS: Age, sex, race, BMI, and HR significantly affect the range of SVG and QRST angles in patients with normal ECGs and no known cardiovascular disease, and should be accounted for in future studies. An online calculator for prediction of these "normal limits" given demographics is provided at https://bivectors.github.io/gehcalc/.

Temporal Trends and Lesion Sets for Persistent Atrial Fibrillation Ablation: A Meta-Analysis With Trial Sequential Analysis and Meta-Regression.

BACKGROUND: Ablation for persistent atrial fibrillation (PsAF) has been performed for over 20 years, although success rates have remained modest. Several adjunctive lesion sets have been studied but none have become standard of practice. We sought to describe how the efficacy of ablation for PsAF has evolved in this time period with a focus on the effect of adjunctive ablation strategies. METHODS: Databases were searched for prospective studies of PsAF ablation. We performed meta-regression and trial sequential analysis. RESULTS: A total of 99 studies (15 424 patients) were included. Ablation for PsAF achieved the primary outcome (freedom of atrial fibrillation/atrial tachycardia rate at 12 months follow-up) in 48.2% (5% CI, 44.0-52.3). Meta-regression showed freedom from atrial arrhythmia at 12 months has improved over time, while procedure time and fluoroscopy time have significantly reduced. Through the use of cumulative meta-analyses and trial sequential analysis, we show that some ablation strategies may initially seem promising, but after several randomized controlled trials may be found to be ineffective. Trial sequential analysis showed that complex fractionated atrial electrogram ablation is ineffective and further study of this treatment would be futile, while posterior wall isolation currently does not have sufficient evidence for routine use in PsAF ablation. CONCLUSIONS: Overall success rates from PsAF ablation and procedure/fluoroscopy times have improved over time. However, no adjunctive lesion set, in addition to pulmonary vein isolation, has been conclusively demonstrated to be beneficial. Through the use of trial sequential analysis, we highlight the importance of adequately powered randomized controlled trials, to avoid reaching premature conclusions, before widespread adoption of novel therapies.

Artificial intelligence-enabled electrocardiogram to distinguish atrioventricular re-entrant tachycardia from atrioventricular nodal re-entrant tachycardia.

Background: Accurately determining arrhythmia mechanism from a 12-lead electrocardiogram (ECG) of supraventricular tachycardia can be challenging. We hypothesized a convolutional neural network (CNN) can be trained to classify atrioventricular re-entrant tachycardia (AVRT) vs atrioventricular nodal re-entrant tachycardia (AVNRT) from the 12-lead ECG, when using findings from the invasive electrophysiology (EP) study as the gold standard. Methods: We trained a CNN on data from 124 patients undergoing EP studies with a final diagnosis of AVRT or AVNRT. A total of 4962 5-second 12-lead ECG segments were used for training. Each case was labeled AVRT or AVNRT based on the findings of the EP study. The model performance was evaluated against a hold-out test set of 31 patients and compared to an existing manual algorithm. Results: The model had an accuracy of 77.4% in distinguishing between AVRT and AVNRT. The area under the receiver operating characteristic curve was 0.80. In comparison, the existing manual algorithm achieved an accuracy of 67.7% on the same test set. Saliency mapping demonstrated the network used the expected sections of the ECGs for diagnoses; these were the QRS complexes that may contain retrograde P waves. Conclusion: We describe the first neural network trained to differentiate AVRT from AVNRT. Accurate diagnosis of arrhythmia mechanism from a 12-lead ECG could aid preprocedural counseling, consent, and procedure planning. The current accuracy from our neural network is modest but may be improved with a larger training dataset.

A fully-automated paper ECG digitisation algorithm using deep learning.

There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed to train NNs, and many ECGs are currently only in paper format, which are not suitable for NN training. We developed a fully-automated online ECG digitisation tool to convert scanned paper ECGs into digital signals. Using automated horizontal and vertical anchor point detection, the algorithm automatically segments the ECG image into separate images for the 12 leads and a dynamical morphological algorithm is then applied to extract the signal of interest. We then validated the performance of the algorithm on 515 digital ECGs, of which 45 were printed, scanned and redigitised. The automated digitisation tool achieved 99.0% correlation between the digitised signals and the ground truth ECG (n = 515 standard 3-by-4 ECGs) after excluding ECGs with overlap of lead signals. Without exclusion, the performance of average correlation was from 90 to 97% across the leads on all 3-by-4 ECGs. There was a 97% correlation for 12-by-1 and 3-by-1 ECG formats after excluding ECGs with overlap of lead signals. Without exclusion, the average correlation of some leads in 12-by-1 ECGs was 60-70% and the average correlation of 3-by-1 ECGs achieved 80-90%. ECGs that were printed, scanned, and redigitised, our tool achieved 96% correlation with the original signals. We have developed and validated a fully-automated, user-friendly, online ECG digitisation tool. Unlike other available tools, this does not require any manual segmentation of ECG signals. Our tool can facilitate the rapid and automated digitisation of large repositories of paper ECGs to allow them to be used for deep learning projects.

Identifying locations susceptible to micro-anatomical reentry using a spatial network representation of atrial fibre maps.

Micro-anatomical reentry has been identified as a potential driver of atrial fibrillation (AF). In this paper, we introduce a novel computational method which aims to identify which atrial regions are most susceptible to micro-reentry. The approach, which considers the structural basis for micro-reentry only, is based on the premise that the accumulation of electrically insulating interstitial fibrosis can be modelled by simulating percolation-like phenomena on spatial networks. Our results suggest that at high coupling, where micro-reentry is rare, the micro-reentrant substrate is highly clustered in areas where the atrial walls are thin and have convex wall morphology, likely facilitating localised treatment via ablation. However, as transverse connections between fibres are removed, mimicking the accumulation of interstitial fibrosis, the substrate becomes less spatially clustered, and the bias to forming in thin, convex regions of the atria is reduced, possibly restricting the efficacy of localised ablation. Comparing our algorithm on image-based models with and without atrial fibre structure, we find that strong longitudinal fibre coupling can suppress the micro-reentrant substrate, whereas regions with disordered fibre orientations have an enhanced risk of micro-reentry. With further development, these methods may be useful for modelling the temporal development of the fibrotic substrate on an individualised basis.

Prognostic Significance of Ventricular Arrhythmias in 13 444 Patients With Acute Coronary Syndrome: A Retrospective Cohort Study Based on Routine Clinical Data (NIHR Health Informatics Collaborative VA-ACS Study).

Background A minority of acute coronary syndrome (ACS) cases are associated with ventricular arrhythmias (VA) and/or cardiac arrest (CA). We investigated the effect of VA/CA at the time of ACS on long-term outcomes. Methods and Results We analyzed routine clinical data from 5 National Health Service trusts in the United Kingdom, collected between 2010 and 2017 by the National Institute for Health Research Health Informatics Collaborative. A total of 13 444 patients with ACS, 376 (2.8%) of whom had concurrent VA, survived to hospital discharge and were followed up for a median of 3.42 years. Patients with VA or CA at index presentation had significantly increased risks of subsequent VA during follow-up (VA group: adjusted hazard ratio [HR], 4.15 [95% CI, 2.42-7.09]; CA group: adjusted HR, 2.60 [95% CI, 1.23-5.48]). Patients who suffered a CA in the context of ACS and survived to discharge also had a 36% increase in long-term mortality (adjusted HR, 1.36 [95% CI, 1.04-1.78]), although the concurrent diagnosis of VA alone during ACS did not affect all-cause mortality (adjusted HR, 1.03 [95% CI, 0.80-1.33]). Conclusions Patients who develop VA or CA during ACS who survive to discharge have increased risks of subsequent VA, whereas those who have CA during ACS also have an increase in long-term mortality. These individuals may represent a subgroup at greater risk of subsequent arrhythmic events as a result of intrinsically lower thresholds for developing VA.

Obesity as a risk factor for cardiac arrhythmias.

Obesity is global health problem with an estimated three billion people worldwide being classified as overweight or obese. In addition to being associated with a range of adverse health outcomes, obesity is linked to higher risks of atrial and ventricular arrhythmias, as well as sudden cardiac death. Obesity is a multifactorial disease that often co-exists with hypertension, diabetes, and sleep apnoea, which are also independent risk factors for cardiac arrhythmias. Nevertheless, compelling evidence suggests that increasing adiposity is an independent proarrhythmic risk factor and that weight loss can be a mitigating and preventative intervention to reduce arrhythmia incidence. This review briefly outlines the economic and social burden of obesity and summarises evidence for the direct and indirect effects of increasing adiposity on risk of atrial and ventricular arrhythmias. The paper also summarises the evidence for electrocardiographic changes indicative of obesity-related atrial and ventricular remodelling and how weight reduction and management of comorbidity might reduce arrhythmic burden.

Artificial intelligence-enabled electrocardiogram to distinguish cavotricuspid isthmus dependence from other atrial tachycardia mechanisms.

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.

Classification of Fibrillation Organisation Using Electrocardiograms to Guide Mechanism-Directed Treatments.

Background: Atrial fibrillation (AF) and ventricular fibrillation (VF) are complex heart rhythm disorders and may be sustained by distinct electrophysiological mechanisms. Disorganised self-perpetuating multiple-wavelets and organised rotational drivers (RDs) localising to specific areas are both possible mechanisms by which fibrillation is sustained. Determining the underlying mechanisms of fibrillation may be helpful in tailoring treatment strategies. We investigated whether global fibrillation organisation, a surrogate for fibrillation mechanism, can be determined from electrocardiograms (ECGs) using band-power (BP) feature analysis and machine learning. Methods: In this study, we proposed a novel ECG classification framework to differentiate fibrillation organisation levels. BP features were derived from surface ECGs and fed to a linear discriminant analysis classifier to predict fibrillation organisation level. Two datasets, single-channel ECGs of rat VF (n = 9) and 12-lead ECGs of human AF (n = 17), were used for model evaluation in a leave-one-out (LOO) manner. Results: The proposed method correctly predicted the organisation level from rat VF ECG with the sensitivity of 75%, specificity of 80%, and accuracy of 78%, and from clinical AF ECG with the sensitivity of 80%, specificity of 92%, and accuracy of 88%. Conclusion: Our proposed method can distinguish between AF/VF of different global organisation levels non-invasively from the ECG alone. This may aid in patient selection and guiding mechanism-directed tailored treatment strategies.

Meta-Analysis of Randomized Controlled Trials of Atrial Fibrillation Ablation With Pulmonary Vein Isolation Versus Without.

OBJECTIVES: This meta-analysis examined the ability of pulmonary vein isolation (PVI) to prevent atrial fibrillation in randomized controlled trials (RCTs) in which the patients not receiving PVI nevertheless underwent a procedure. BACKGROUND: PVI is a commonly used procedure for the treatment of atrial fibrillation (AF), and its efficacy has usually been judged against therapy with anti-arrhythmic drugs in open-label trials. There have been several RCTs of AF ablation in which both arms received an ablation, but the difference between the treatment arms was inclusion or omission of PVI. These trials of an ablation strategy with PVI versus an ablation strategy without PVI may provide a more rigorous method for evaluating the efficacy of PVI. METHODS: Medline and Cochrane databases were searched for RCTs comparing ablation including PVI with ablation excluding PVI. The primary efficacy endpoint was freedom from atrial fibrillation (AF) and atrial tachycardia at 12 months. A random-effects meta-analysis was performed using the restricted maximum likelihood estimator. RESULTS: Overall, 6 studies (n = 610) met inclusion criteria. AF recurrence was significantly lower with an ablation including PVI than an ablation without PVI (RR: 0.54; 95% confidence interval [CI]: 0.33 to 0.89; p = 0.0147; I2 = 79.7%). Neither the type of AF (p = 0.48) nor the type of non-PVI ablation (p = 0.21) was a significant moderator of the effect size. In 3 trials the non-PVI ablation procedure was performed in both arms, whereas PVI was performed in only 1 arm. In these studies, AF recurrence was significantly lower when PVI was included (RR: 0.32; 95% CI: 0.14 to 0.73; p = 0.007, I2 78%). CONCLUSIONS: In RCTs where both arms received an ablation, and therefore an expectation amongst patients and doctors of benefit, being randomized to PVI had a striking effect, reducing AF recurrence by a half.