Machine Learned Cellular Phenotypes in Cardiomyopathy Predict Sudden Death

Impact of artificial intelligence arrhythmia mapping on time to first ablation, procedure duration, and fluoroscopy use

INTRODUCTION

Artificial intelligence (AI) ECG arrhythmia mapping provides arrhythmia source localization using 12-lead ECG data; whether this information impacts procedural efficiency is unknown. We performed a retrospective, case-control study to evaluate the hypothesis that AI ECG mapping may reduce time to ablation, procedural duration, and fluoroscopy.

MATERIALS AND METHODS

Cases in which system output was used were retrospectively enrolled according to IRB-approved protocols at each site. Matched control cases were enrolled in reverse chronological order beginning on the last day for which the technology was unavailable. Controls were matched based upon physician, institution, arrhythmia, and a predetermined complexity rating. Procedural metrics, fluoroscopy data, and clinical outcomes were assessed from time-stamped medical records.

RESULTS

The study group consisted of 28 patients (age 65 ± 11 years, 46% female, left atrial dimension 4.1 ± 0.9 cm, LVEF 50 ± 18%) and was similar to 28 controls. The most common arrhythmia types were atrial fibrillation (n = 10), premature ventricular complexes (n = 8), and ventricular tachycardia (n = 6). Use of the system was associated with a 19.0% reduction in time to ablation (133 ± 48 vs. 165 ± 49 min, p = 0.02), a 22.6% reduction in procedure duration (233 ± 51 vs. 301 ± 83 min, p < 0.001), and a 43.7% reduction in fluoroscopy (18.7 ± 13.3 vs. 33.2 ± 18.0 min, p < 0.001) versus controls. At 6 months follow-up, arrhythmia-free survival was 73.5% in the study group and 63.3% in the control group (p = 0.56).

CONCLUSION

Use of forward-solution AI ECG mapping is associated with reductions in time to first ablation, procedure duration, and fluoroscopy without an adverse impact on procedure outcomes or complications.

In silico study of the mechanisms of hypoxia and contractile dysfunction during ischemia and reperfusion of hiPSC cardiomyocytes

Interconnected mechanisms of ischemia and reperfusion (IR) has increased the interest in IR in vitro experiments using human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs). We developed a whole-cell computational model of hiPSC-CMs including the electromechanics, a metabolite-sensitive sarcoplasmic reticulum Ca2+-ATPase (SERCA) and an oxygen dynamics formulation to investigate IR mechanisms. Moreover, we simulated the effect and action mechanism of levosimendan, which recently showed promising anti-arrhythmic effects in hiPSC-CMs in hypoxia. The model was validated using hiPSC-CM and in vitro animal data. The role of SERCA in causing relaxation dysfunction in IR was anticipated to be comparable to its function in sepsis-induced heart failure. Drug simulations showed that levosimendan counteracts the relaxation dysfunction by utilizing a particular Ca2+-sensitizing mechanism involving Ca2+-bound troponin C and Ca2+ flux to the myofilament, rather than inhibiting SERCA phosphorylation. The model demonstrates extensive characterization and promise for drug development, making it suitable for evaluating IR therapy strategies based on the changing levels of cardiac metabolites, oxygen and molecular pathways.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

An ECG-based artificial intelligence model for assessment of sudden cardiac death risk

BACKGROUND

Conventional ECG-based algorithms could contribute to sudden cardiac death (SCD) risk stratification but demonstrate moderate predictive capabilities. Deep learning (DL) models use the entire digital signal and could potentially improve predictive power. We aimed to train and validate a 12 lead ECG-based DL algorithm for SCD risk assessment.

METHODS

Out-of-hospital SCD cases were prospectively ascertained in the Portland, Oregon, metro area. A total of 1,827 pre- cardiac arrest 12 lead ECGs from 1,796 SCD cases were retrospectively collected and analyzed to develop an ECG-based DL model. External validation was performed in 714 ECGs from 714 SCD cases from Ventura County, CA. Two separate control group samples were obtained from 1342 ECGs taken from 1325 individuals of which at least 50% had established coronary artery disease. The DL model was compared with a previously validated conventional 6 variable ECG risk model.

RESULTS

The DL model achieves an AUROC of 0.889 (95% CI 0.861-0.917) for the detection of SCD cases vs. controls in the internal held-out test dataset, and is successfully validated in external SCD cases with an AUROC of 0.820 (0.794-0.847). The DL model performs significantly better than the conventional ECG model that achieves an AUROC of 0.712 (0.668-0.756) in the internal and 0.743 (0.711-0.775) in the external cohort.

CONCLUSIONS

An ECG-based DL model distinguishes SCD cases from controls with improved accuracy and performs better than a conventional ECG risk model. Further detailed investigation is warranted to evaluate how the DL model could contribute to improved SCD risk stratification.

Risk prediction of inappropriate implantable cardioverter-defibrillator therapy using machine learning

We aimed to develop machine learning-based predictive models for identifying inappropriate implantable cardioverter-defibrillator (ICD) therapy. Our study included 182 consecutive cases (average age 62.2 ± 4.5 years, 169 men) and employed 14 non-deep learning models for prediction (hold-out method). These models utilized selected electrocardiogram parameters and clinical features collected after ICD implantation. From the feature importance analysis of the best ML model, we established easily calculable scores. Among the patients, 25 (13.7%) experienced inappropriate therapy, and we identified 16 significant predictors. Using recursive feature elimination with cross-validation, we reduced the features to six with high feature importance: history of atrial arrhythmia (Atr-arrhythm), ischemic cardiomyopathy (ICM), absence of diabetes mellitus (DM), lack of cardiac resynchronization therapy (CRT), V3 ST level at J point (V3 STJ), and V5 R-wave amplitudes (V5R amp). The extra-trees classifier yielded the highest area under receiver operating characteristics curve (AUROC; 0.869 on test data). Thus, the Cardi35 score was defined as [+ 5.5*Atr-arrhythm - 1.5*CRT + 1.0*V3STJ + 1.0*V5R - 1.0*ICM - 0.5*DM], which demonstrated a hazard ratio of 1.62 (P < 0.001). A cut-off value of the score + 5.5 showed high AUROC (0.826). The ML approach can yield a robust prediction model, and the Cardi35 score was a convenient predictor for inappropriate therapy.

The Lancet Commission to reduce the global burden of sudden cardiac death: a call for multidisciplinary action

Despite major advancements in cardiovascular medicine, sudden cardiac death (SCD) continues to be an enormous medical and societal challenge, claiming millions of lives every year. Efforts to prevent SCD are hampered by imperfect risk prediction and inadequate solutions to specifically address arrhythmogenesis. Although resuscitation strategies have witnessed substantial evolution, there is a need to strengthen the organisation of community interventions and emergency medical systems across varied locations and health-care structures. With all the technological and medical advances of the 21st century, the fact that survival from sudden cardiac arrest (SCA) remains lower than 10% in most parts of the world is unacceptable. Recognising this urgent need, the Lancet Commission on SCD was constituted, bringing together 30 international experts in varied disciplines. Consistent progress in tackling SCD will require a completely revamped approach to SCD prevention, with wide-sweeping policy changes that will empower the development of both governmental and community-based programmes to maximise survival from SCA, and to comprehensively attend to survivors and decedents' families after the event. International collaborative efforts that maximally leverage and connect the expertise of various research organisations will need to be prioritised to properly address identified gaps. The Commission places substantial emphasis on the need to develop a multidisciplinary strategy that encompasses all aspects of SCD prevention and treatment. The Commission provides a critical assessment of the current scientific efforts in the field, and puts forth key recommendations to challenge, activate, and intensify efforts by both the scientific and global community with new directions, research, and innovation to reduce the burden of SCD worldwide.

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.

Artificial Intelligence in Ventricular Arrhythmias and Sudden Death

Sudden cardiac arrest due to lethal ventricular arrhythmias is a major cause of mortality worldwide and results in more years of potential life lost than any individual cancer. Most of these sudden cardiac arrest events occur unexpectedly in individuals who have not been identified as high-risk due to the inadequacy of current risk stratification tools. Artificial intelligence tools are increasingly being used to solve complex problems and are poised to help with this major unmet need in the field of clinical electrophysiology. By leveraging large and detailed datasets, artificial intelligence-based prediction models have the potential to enhance the risk stratification of lethal ventricular arrhythmias. This review presents a synthesis of the published literature and a discussion of future directions in this field.

Primer on Machine Learning in Electrophysiology

Artificial intelligence has become ubiquitous. Machine learning, a branch of artificial intelligence, leads the current technological revolution through its remarkable ability to learn and perform on data sets of varying types. Machine learning applications are expected to change contemporary medicine as they are brought into mainstream clinical practice. In the field of cardiac arrhythmia and electrophysiology, machine learning applications have enjoyed rapid growth and popularity. To facilitate clinical acceptance of these methodologies, it is important to promote general knowledge of machine learning in the wider community and continue to highlight the areas of successful application. The authors present a primer to provide an overview of common supervised (least squares, support vector machine, neural networks and random forest) and unsupervised (k-means and principal component analysis) machine learning models. The authors also provide explanations as to how and why the specific machine learning models have been used in arrhythmia and electrophysiology studies.

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).

Improving the hERG model fitting using a deep learning-based method

The hERG channel is one of the essential ion channels composing the cardiac action potential and the toxicity assay for new drug. Recently, the comprehensive in vitro proarrhythmia assay (CiPA) was adopted for cardiac toxicity evaluation. One of the hurdles for this protocol is identifying the kinetic effect of the new drug on the hERG channel. This procedure included the model-based parameter identification from the experiments. There are many mathematical methods to infer the parameters; however, there are two main difficulties in fitting parameters. The first is that, depending on the data and model, parametric inference can be highly time-consuming. The second is that the fitting can fail due to local minima problems. The simplest and most effective way to solve these issues is to provide an appropriate initial value. In this study, we propose a deep learning-based method for improving model fitting by providing appropriate initial values, even the right answer. We generated the dataset by changing the model parameters and trained our deep learning-based model. To improve the accuracy, we used the spectrogram with time, frequency, and amplitude. We obtained the experimental dataset from https://github.com/CardiacModelling/hERGRapidCharacterisation. Then, we trained the deep-learning model using the data generated with the hERG model and tested the validity of the deep-learning model with the experimental data. We successfully identified the initial value, significantly improved the fitting speed, and avoided fitting failure. This method is useful when the model is fixed and reflects the real data, and it can be applied to any in silico model for various purposes, such as new drug development, toxicity identification, environmental effect, etc. This method will significantly reduce the time and effort to analyze the data.

Emerging role of artificial intelligence in cardiac electrophysiology

Artificial intelligence (AI) and machine learning (ML) have significantly impacted the field of cardiovascular medicine, especially cardiac electrophysiology (EP), on multiple fronts. The goal of this review is to familiarize readers with the field of AI and ML and their emerging role in EP. The current review is divided into 3 sections. In the first section, we discuss the definitions and basics of AI, ML, and big data. In the second section, we discuss their application to EP in the context of detection, prediction, and management of arrhythmias. Finally, we discuss the regulatory issues, challenges, and future directions of AI in EP.

The physics of heart rhythm disorders

The global burden caused by cardiovascular disease is substantial, with heart disease representing the most common cause of death around the world. There remains a need to develop better mechanistic models of cardiac function in order to combat this health concern. Heart rhythm disorders, or arrhythmias, are one particular type of disease which has been amenable to quantitative investigation. Here we review the application of quantitative methodologies to explore dynamical questions pertaining to arrhythmias. We begin by describing single-cell models of cardiac myocytes, from which two and three dimensional models can be constructed. Special focus is placed on results relating to pattern formation across these spatially-distributed systems, especially the formation of spiral waves of activation. Next, we discuss mechanisms which can lead to the initiation of arrhythmias, focusing on the dynamical state of spatially discordant alternans, and outline proposed mechanisms perpetuating arrhythmias such as fibrillation. We then review experimental and clinical results related to the spatio-temporal mapping of heart rhythm disorders. Finally, we describe treatment options for heart rhythm disorders and demonstrate how statistical physics tools can provide insights into the dynamics of heart rhythm disorders.

Forward-Solution Noninvasive Computational Arrhythmia Mapping: The VMAP Study

BACKGROUND

The accuracy of noninvasive arrhythmia source localization using a forward-solution computational mapping system has not yet been evaluated in blinded, multicenter analysis. This study tested the hypothesis that a computational mapping system incorporating a comprehensive arrhythmia simulation library would provide accurate localization of the site-of-origin for atrial and ventricular arrhythmias and pacing using 12-lead ECG data when compared with the gold standard of invasive electrophysiology study and ablation.

METHODS

The VMAP study (Vectorcardiographic Mapping of Arrhythmogenic Probability) was a blinded, multicenter evaluation with final data analysis performed by an independent core laboratory. Eligible episodes included atrial and ventricular: tachycardia, fibrillation, pacing, premature atrial and ventricular complexes, and orthodromic atrioventricular reentrant tachycardia. Mapping system results were compared with the gold standard site of successful ablation or pacing during electrophysiology study and ablation. Mapping time was assessed from time-stamped logs. Prespecified performance goals were used for statistical comparisons.

RESULTS

A total of 255 episodes from 225 patients were enrolled from 4 centers. Regional accuracy for ventricular tachycardia and premature ventricular complexes in patients without significant structural heart disease (n=75, primary end point) was 98.7% (95% CI, 96.0%-100%; P<0.001 to reject predefined H0 <0.80). Regional accuracy for all episodes (secondary end point 1) was 96.9% (95% CI, 94.7%-99.0%; P<0.001 to reject predefined H0 <0.75). Accuracy for the exact or neighboring segment for all episodes (secondary end point 2) was 97.3% (95% CI, 95.2%-99.3%; P<0.001 to reject predefined H0 <0.70). Median spatial accuracy was 15 mm (n=255, interquartile range, 7-25 mm). The mapping process was completed in a median of 0.8 minutes (interquartile range, 0.4-1.4 minutes).

CONCLUSIONS

Computational ECG mapping using a forward-solution approach exceeded prespecified accuracy goals for arrhythmia and pacing localization. Spatial accuracy analysis demonstrated clinically actionable results. This rapid, noninvasive mapping technology may facilitate catheter-based and noninvasive targeted arrhythmia therapies.

REGISTRATION

URL: https://www.

CLINICALTRIALS

gov; Unique identifier: NCT04559061.

Minor perturbations of thyroid homeostasis and major cardiovascular endpoints—Physiological mechanisms and clinical evidence

It is well established that thyroid dysfunction is linked to an increased risk of cardiovascular morbidity and mortality. The pleiotropic action of thyroid hormones strongly impacts the cardiovascular system and affects both the generation of the normal heart rhythm and arrhythmia. A meta-analysis of published evidence suggests a positive association of FT4 concentration with major adverse cardiovascular end points (MACE), but this association only partially extends to TSH. The risk for cardiovascular death is increased in both subclinical hypothyroidism and subclinical thyrotoxicosis. Several published studies found associations of TSH and FT4 concentrations, respectively, with major cardiovascular endpoints. Both reduced and elevated TSH concentrations predict the cardiovascular risk, and this association extends to TSH gradients within the reference range. Likewise, increased FT4 concentrations, but high-normal FT4 within its reference range as well, herald a poor outcome. These observations translate to a monotonic and sensitive effect of FT4 and a U-shaped relationship between TSH and cardiovascular risk. Up to now, the pathophysiological mechanism of this complex pattern of association is poorly understood. Integrating the available evidence suggests a dual etiology of elevated FT4 concentration, comprising both ensuing primary hypothyroidism and a raised set point of thyroid function, e. g. in the context of psychiatric disease, chronic stress and type 2 allostatic load. Addressing the association between thyroid homeostasis and cardiovascular diseases from a systems perspective could pave the way to new directions of research and a more personalized approach to the treatment of patients with cardiovascular risk.

Machine Learning-Enabled Multimodal Fusion of Intra-Atrial and Body Surface Signals in Prediction of Atrial Fibrillation Ablation Outcomes

BACKGROUND

Machine learning is a promising approach to personalize atrial fibrillation management strategies for patients after catheter ablation. Prior atrial fibrillation ablation outcome prediction studies applied classical machine learning methods to hand-crafted clinical scores, and none have leveraged intracardiac electrograms or 12-lead surface electrocardiograms for outcome prediction. We hypothesized that (1) machine learning models trained on electrograms or electrocardiogram (ECG) signals can perform better at predicting patient outcomes after atrial fibrillation ablation than existing clinical scores and (2) multimodal fusion of electrogram, ECG, and clinical features can further improve the prediction of patient outcomes.

METHODS

Consecutive patients who underwent catheter ablation between 2015 and 2017 with panoramic left atrial electrogram before ablation and clinical follow-up for at least 1 year following ablation were included. Convolutional neural network and a novel multimodal fusion framework were developed for predicting 1-year atrial fibrillation recurrence after catheter ablation from electrogram, ECG signals, and clinical features. The models were trained and validated using 10-fold cross-validation on patient-level splits.

RESULTS

One hundred fifty-six patients (64.5±10.5 years, 74% male, 42% paroxysmal) were analyzed. Using electrogram signals alone, the convolutional neural network achieved an area under the receiver operating characteristics curve (AUROC) of 0.731, outperforming the existing APPLE scores (AUROC=0.644) and CHA2DS2-VASc scores (AUROC=0.650). Similarly using 12-lead ECG alone, the convolutional neural network achieved an AUROC of 0.767. Combining electrogram, ECG, and clinical features, the fusion model achieved an AUROC of 0.859, outperforming single and dual modality models.

CONCLUSIONS

Deep neural networks trained on electrogram or ECG signals improved the prediction of catheter ablation outcome compared with existing clinical scores, and fusion of electrogram, ECG, and clinical features further improved the prediction. This suggests the promise of using machine learning to help treatment planning for patients after catheter ablation.

Atrial fibrillation signatures on intracardiac electrograms identified by deep learning

BACKGROUND

Automatic detection of atrial fibrillation (AF) by cardiac devices is increasingly common yet suboptimally groups AF, flutter or tachycardia (AT) together as 'high rate events'. This may delay or misdirect therapy.

OBJECTIVE

We hypothesized that deep learning (DL) can accurately classify AF from AT by revealing electrogram (EGM) signatures.

METHODS

We studied 86 patients in whom the diagnosis of AF or AT was established at electrophysiological study (25 female, 65 ± 11 years). Custom DL architectures were trained to identify AF using N = 29,340 unipolar and N = 23,760 bipolar EGM segments. We compared DL to traditional classifiers based on rate or regularity. We explained DL using computer models to assess the impact of controlled variations in shape, rate and timing on AF/AT classification in 246,067 EGMs reconstructed from clinical data.

RESULTS

DL identified AF with AUC of 0.97 ± 0.04 (unipolar) and 0.92 ± 0.09 (bipolar). Rule-based classifiers misclassified ∼10-12% of cases. DL classification was explained by regularity in EGM shape (13%) or timing (26%), and rate (60%; p < 0.001), and also by a set of unipolar EGM shapes that classified as AF independent of rate or regularity. Overall, the optimal AF 'fingerprint' comprised these specific EGM shapes, >15% timing variation, <0.48 correlation in beat-to-beat EGM shapes and CL < 190 ms (p < 0.001).

CONCLUSIONS

Deep learning of intracardiac EGMs can identify AF or AT via signatures of rate, regularity in timing or shape, and specific EGM shapes. Future work should examine if these signatures differ between different clinical subpopulations with AF.

Machine learning techniques for arrhythmic risk stratification: a review of the literature

Ventricular arrhythmias (VAs) and sudden cardiac death (SCD) are significant adverse events that affect the morbidity and mortality of both the general population and patients with predisposing cardiovascular risk factors. Currently, conventional disease-specific scores are used for risk stratification purposes. However, these risk scores have several limitations, including variations among validation cohorts, the inclusion of a limited number of predictors while omitting important variables, as well as hidden relationships between predictors. Machine learning (ML) techniques are based on algorithms that describe intervariable relationships. Recent studies have implemented ML techniques to construct models for the prediction of fatal VAs. However, the application of ML study findings is limited by the absence of established frameworks for its implementation, in addition to clinicians’ unfamiliarity with ML techniques. This review, therefore, aims to provide an accessible and easy-to-understand summary of the existing evidence about the use of ML techniques in the prediction of VAs. Our findings suggest that ML algorithms improve arrhythmic prediction performance in different clinical settings. However, it should be emphasized that prospective studies comparing ML algorithms to conventional risk models are needed while a regulatory framework is required prior to their implementation in clinical practice.

Big Data in electrophysiology

The quantity of data produced and captured in medicine today is unprecedented. Technological improvements and automation have expanded the traditional statistical methods and enabled the analysis of Big Data. This has permitted the discovery of new associations with a granularity that was previously hidden to human eyes. In the first part of this review, the authors would like to provide an overview of basic Machine Learning (ML) principles and techniques in order to better understand their application in recent publications about cardiac arrhythmias. In the second part, ML-enabled advances in disease detection and diagnosis, outcome prediction, and novel disease characterization in topics like electrocardiography, atrial fibrillation, ventricular arrhythmias, and cardiac devices are presented. Finally, the limitations and challenges of applying ML in clinical practice, such as validation, replication, generalizability, and regulatory issues, are discussed. More carefully designed studies and collaborations are needed for ML to become feasible, trustworthy, accurate, and reproducible and to reach its full potential for patient-oriented precision medicine.

Identifying Atrial Fibrillation Mechanisms for Personalized Medicine

Atrial fibrillation (AF) is a major cause of heart failure and stroke. The early maintenance of sinus rhythm has been shown to reduce major cardiovascular endpoints, yet is difficult to achieve. For instance, it is unclear how discoveries at the genetic and cellular level can be used to tailor pharmacotherapy. For non-pharmacologic therapy, pulmonary vein isolation (PVI) remains the cornerstone of rhythm control, yet has suboptimal success. Improving these therapies will likely require a multifaceted approach that personalizes therapy based on mechanisms measured in individuals across biological scales. We review AF mechanisms from cell-to-organ-to-patient from this perspective of personalized medicine, linking them to potential clinical indices and biomarkers, and discuss how these data could influence therapy. We conclude by describing approaches to improve ablation, including the emergence of several mapping systems that are in use today.

Ventricular voltage-gated ion channels: Detection, characteristics, mechanisms, and drug safety evaluation

Cardiac voltage-gated ion channels (VGICs) play critical roles in mediating cardiac electrophysiological signals, such as action potentials, to maintain normal heart excitability and contraction. Inherited or acquired alterations in the structure, expression, or function of VGICs, as well as VGIC-related side effects of pharmaceutical drug delivery can result in abnormal cellular electrophysiological processes that induce life-threatening cardiac arrhythmias or even sudden cardiac death. Hence, to reduce possible heart-related risks, VGICs must be acknowledged as important targets in drug discovery and safety studies related to cardiac disease. In this review, we first summarize the development and application of electrophysiological techniques that are employed in cardiac VGIC studies alone or in combination with other techniques such as cryoelectron microscopy, optical imaging and optogenetics. Subsequently, we describe the characteristics, structure, mechanisms, and functions of various well-studied VGICs in ventricular myocytes and analyze their roles in and contributions to both physiological cardiac excitability and inherited cardiac diseases. Finally, we address the implications of the structure and function of ventricular VGICs for drug safety evaluation. In summary, multidisciplinary studies on VGICs help researchers discover potential targets of VGICs and novel VGICs in heart, enrich their knowledge of the properties and functions, determine the operation mechanisms of pathological VGICs, and introduce groundbreaking trends in drug therapy strategies, and drug safety evaluation.

The Role of Artificial Intelligence and Machine Learning in Clinical Cardiac Electrophysiology

In recent years, artificial intelligence (AI) has found numerous applications in cardiology due in part to large digitized datasets and the evolution of high performance computing. In the discipline of cardiac electrophysiology (EP), a number of clinical, imaging, and electrical waveform data are considered in the diagnosis, prognostication and management of arrhythmias, which lend themselves well to automation through AI. But equally relevant, AI offers a unique opportunity to discover novel EP concepts and improve clinical care through its inherent, hierarchical tenets of self-learning. This review will focus on the application of AI in clinical EP and summarize state-of-the art, large, clinical studies in the following key domains: (1) ECG-based arrhythmia and disease classification, (2) atrial fibrillation source detection, (3) substrate and risk assessment for atrial fibrillation and ventricular tachyarrhythmias, and (4) predicting outcomes after cardiac resynchronization therapy. Many are small, single-center, proof-of-concept investigations, but they still demonstrate groundbreaking performance of deep learning, a subdomain of AI, which surpasses traditional statistical analysis. Larger studies, for instance classifying arrhythmias from ECG recordings, have further provided external validation of their high accuracy. Ultimately, the performance of AI is dependent on the quality of the input data and the rigor of algorithm development. The field is still nascent and several barriers will need to be overcome, including prospective validation in large, well-labelled datasets and more seamless information technology-based data collection/integration, before AI can be adopted into broader clinical EP practice. This review will conclude with a discussion of these challenges and future work.

A deep learning algorithm to translate and classify cardiac electrophysiology

The development of induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) has been a critical in vitro advance in the study of patient-specific physiology, pathophysiology, and pharmacology. We designed a new deep learning multitask network approach intended to address the low throughput, high variability, and immature phenotype of the iPSC-CM platform. The rationale for combining translation and classification tasks is because the most likely application of the deep learning technology we describe here is to translate iPSC-CMs following application of a perturbation. The deep learning network was trained using simulated action potential (AP) data and applied to classify cells into the drug-free and drugged categories and to predict the impact of electrophysiological perturbation across the continuum of aging from the immature iPSC-CMs to the adult ventricular myocytes. The phase of the AP extremely sensitive to perturbation due to a steep rise of the membrane resistance was found to contain the key information required for successful network multitasking. We also demonstrated successful translation of both experimental and simulated iPSC-CM AP data validating our network by prediction of experimental drug-induced effects on adult cardiomyocyte APs by the latter.

Machine Learning in Arrhythmia and Electrophysiology

Machine learning (ML), a branch of artificial intelligence, where machines learn from big data, is at the crest of a technological wave of change sweeping society. Cardiovascular medicine is at the forefront of many ML applications, and there is a significant effort to bring them into mainstream clinical practice. In the field of cardiac electrophysiology, ML applications have also seen a rapid growth and popularity, particularly the use of ML in the automatic interpretation of ECGs, which has been extensively covered in the literature. Much lesser known are the other aspects of ML application in cardiac electrophysiology and arrhythmias, such as those in basic science research on arrhythmia mechanisms, both experimental and computational; in the development of better techniques for mapping of cardiac electrical function; and in translational research related to arrhythmia management. In the current review, we examine comprehensively such ML applications as they match the scope of this journal. The current review is organized in 3 parts. The first provides an overview of general ML principles and methodologies that will afford readers of the necessary information on the subject, serving as the foundation for inviting further ML applications in arrhythmia research. The basic information we provide can serve as a guide on how one might design and conduct an ML study. The second part is a review of arrhythmia and electrophysiology studies in which ML has been utilized, highlighting the broad potential of ML approaches. For each subject, we outline comprehensively the general topics, while reviewing some of the research advances utilizing ML under the subject. Finally, we discuss the main challenges and the perspectives for ML-driven cardiac electrophysiology and arrhythmia research.

Artificial intelligence for a personalized diagnosis and treatment of atrial fibrillation

Although atrial fibrillation (AF) is the most common cardiac arrhythmia, its early identification, diagnosis, and treatment is still challenging. Due to its heterogeneous mechanisms and risk factors, targeting an individualized treatment of AF demands a large amount of patient data to identify specific patterns. Artificial intelligence (AI) algorithms are particularly well suited for treating high-dimensional data, predicting outcomes, and eventually, optimizing strategies for patient management. The analysis of large patient samples combining different sources of information such as blood biomarkers, electrical signals, and medical images opens a new paradigm for improving diagnostic algorithms. In this review, we summarize suitable AI techniques for this purpose. In particular, we describe potential applications for understanding the structural and functional bases of the disease, as well as for improving early noninvasive diagnosis, developing more efficient therapies, and predicting long-term clinical outcomes of patients with AF.