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.

Year in Review in Cardiac Electrophysiology

In the past year, there have been numerous advances in our understanding of arrhythmia mechanisms, diagnosis, and new therapies. We have seen advances in basic cardiac electrophysiology with data suggesting that secretoneurin may be a biomarker for patients at risk of ventricular arrhythmias, and we have learned of the potential role of an NPR-C (natriuretic peptide receptor-C) in atrial fibrosis and the role of an atrial specific 2-pore potassium channel TASK-1 as a therapeutic target for atrial fibrillation. We have seen studies demonstrating the role of sensory neurons in sleep apnea–related atrial fibrillation and the association between bariatric surgery and atrial fibrillation ablation outcomes. Artificial intelligence applied to electrocardiography has yielded estimates of age, sex, and overall health. We have seen new tools for collection of patient-centered outcomes following catheter ablation. There have been significant advances in the ability to identify ventricular tachycardia termination sites through high-density mapping of deceleration zones. We have learned that right ventricular dysfunction may be a predictor of survival benefit after implantable cardioverter-defibrillator implantation in patients with nonischemic cardiomyopathy. We have seen further insights into the role of His bundle pacing on improving outcomes. As our understanding of cardiac laminopathies advances, we may have new tools to predict arrhythmic event rates in gene carriers. Finally, we have seen numerous advances in the treatment of arrhythmias in patients with congenital heart disease.

Proarrhythmic Effects of Electrolyte Imbalance in Virtual Human Atrial and Ventricular Cardiomyocytes

Dialysis is prescribed to renal failure patients as a long-term chronic treatment. Whereas dialysis therapeutically normalizes serum electrolytes and removes small toxin molecules, it fails to alleviate fibroblast induced structural fibrosis, and unresponsive uremia. The simultaneous presence of altered electrolytes and fibrosis or uremia is thought to be pro-arrhythmogenic. This study explored potential arrhythmogenesis under pre-dialysis (high electrolyte levels) and post-dialysis (low physiological electrolyte levels) in the presence of fibrosis and uremia in human atrial and ventricular model cardiomyocytes.Two validated human cardiomyocyte models were used in this study that permitted simulation of cardiac atrial and ventricular detailed electrophysiology. Pathological conditions simulating active fibrosis and uremia were implemented in both models. Pre- and post-dialysis conditions were simulated using high and low electrolyte levels respectively. Arrythmogenesis was quantified by computing restitution curves that permitted identification of action potential duration and calcium transient alternans instabilities. In comparison to control conditions, fibrosis abbreviated action potential durations while uremia prolonged the same. Under pre-dialysis conditions, an elevation of serum electrolyte levels caused action potential durations to be abbreviated under both fibrosis and uremia. Alternans instability was observed in the ventricular cardiomyocyte model. Under post-dialysis conditions, lower levels of serum electrolytes promoted an abbreviated action potential duration under fibrosis but caused a large increase of the control and uremic action potential durations. Alternans instabilities were observed in the atrial cardiomyocyte model under post-dialysis conditions at physiological heart rates. The calcium transient restitution showed similar alternans instabilities. Co-existing conditions such as fibrosis and uremia in the presence of unphysiological electrolyte levels promote arrhythmogenesis and may require additional treatment to improve dialysis outcomes.Clinical Relevance. Knowledge of model response to clinically relevant conditions permits use of in silico modeling to better understand and dissect underlying arrhythmia mechanisms.

Complementarity between Arrhythmia Mechanisms Found in Silico and in Genetic Models of N588K-hERG Linked Short QT Syndrome

Congenital Short QT Syndrome (SQTS) is a rare but dangerous condition involving abbreviated ventricular repolarization and an increased risk of atrial and ventricular arrhythmias. Taking the example of the first identified SQTS mutation, N588K-hERG, we consider briefly the basic science approaches used to obtain an understanding of the mechanism(s) of arrhythmogenesis in this form of the syndrome. A combination of recombinant channel electrophysiology and in silico simulations has provided insights into causality between the identified mutation, accelerated repolarization and increased susceptibility to re-entry in N588K-hERG-linked SQTS. Subsequent studies employing a transgenic rabbit model or human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) have further demonstrated mechanisms predisposing to re-entry, spiral wave activity and arrhythmia in intact tissue. The complementarity between the findings made using these different approaches gives confidence that, collectively, they have identified major arrhythmia mechanisms and their potential mitigation by Class I antiarrhythmic drugs in this form of SQTS.

Clinical evidence-guided network pharmacology analysis reveals a critical contribution of β1-adrenoreceptor upregulation to bradycardia alleviation by Shenxian-Shengmai

Background Shenxian-Shengmai (SXSM) Oral Liquid is a CFDA-approved patent Chinese Herbal medicine, which has been clinically used for the treatment of bradycardia. However, its active components and action mechanism remain to be established. The present study aimed to evaluate the efficacy of SXSM on bradycardia and to identify the possible active components and their pharmacological targets for this action. Methods A literature-based meta-analysis was performed to evaluate the clinical efficacy of SXSM on bradycardia, which was confirmed by a rat ex vivo cardiac model. Network pharmacology analysis was then conducted to reveal the potential targets of SXSM active components and their anti-arrhythmia mechanisms. Finally, the identified drug-target interaction was confirmed by immunofluorescence assay in cardiomyocyte. Results Meta-analysis of the available clinical study data shows that Shenxian-Shengmai Oral Liquid has a favorable effect for bradycardia. In an ex vivo bradycardia model of rat heart, SXSM restored heart rate by affecting Heart rate variability (HRV) which is associated with autonomic nervous system activity. A drug-target-pathway network analysis connecting SXSM components with arrhythmia suggested that a prominent anti-arrhythmia mechanisms of SXSM was via β1-adrenergic signaling pathway, which was subsequently validated by immunofluorescence assay showing that SXSM indeed increased the expression of ADRB1 in cultured cardiomyocytes. Conclusion By combining approaches of clinical evidence mining, experimental model confirmation, network pharmacology analyses and molecular mechanistic validation, we show that SXSM is an effective treatment for bradycardia and it involves multiple component interacting via multiple pathways, among which is the critical β1-adrenergic receptor upregulation. Our integrative approach could be applied to other multi-component traditional Chinese medicine investigation where ample clinical data are accumulated but advanced mechanistic studies are lacking.