The potential of artificial intelligence to revolutionize health care delivery, research, and education in cardiac electrophysiology.

The field of electrophysiology (EP) has benefited from numerous seminal innovations and discoveries that have enabled clinicians to deliver therapies and interventions that save lives and promote quality of life. The rapid pace of innovation in EP may be hindered by several challenges including the aging population with increasing morbidity, the availability of multiple costly therapies that, in many instances, confer minor incremental benefit, the limitations of healthcare reimbursement, the lack of response to therapies by some patients, and the complications of the invasive procedures performed. To overcome these challenges and continue on a steadfast path of transformative innovation, the EP community must comprehensively explore how artificial intelligence (AI) can be applied to healthcare delivery, research, and education and consider all opportunities in which AI can catalyze innovation; create workflow, research, and education efficiencies; and improve patient outcomes at a lower cost. In this white paper, we define AI and discuss the potential of AI to revolutionize the EP field. We also address the requirements for implementing, maintaining, and enhancing quality when using AI and consider ethical, operational, and regulatory aspects of AI implementation. This manuscript will be followed by several perspective papers that will expand on some of these topics.

Ventricular Intramyocardial Navigation for Tachycardia Ablation Guided by Electrograms (VINTAGE): Deep Ablation in Inaccessible Targets.

BACKGROUND: Deep intramural ventricular tachycardia substrate targets are difficult to access, map, and ablate from endocardial and epicardial surfaces, resulting in high recurrence rates. OBJECTIVES: In this study, the authors introduce a novel approach called ventricular intramyocardial navigation for tachycardia ablation guided by electrograms (VINTAGE) to access and ablate anatomically challenging ventricular tachycardia from within the myocardium. METHODS: Guidewire/microcatheter combinations were navigated deep throughout the extravascular myocardium, accessed directly from the right ventricle cavity, in Yorkshire swine (6 naive, 1 infarcted). Devices were steered to various intramyocardial targets including the left ventricle summit, guided by fluoroscopy, unipolar electrograms, and/or electroanatomic mapping. Radiofrequency ablations were performed to characterize ablation parameters and reproducibility. Intramyocardial saline irrigation began 1 minute before ablation and continued throughout. Lesions were analyzed on cardiac magnetic resonance and necropsy. RESULTS: VINTAGE was feasible in all animals within naive and infarcted myocardium. Forty-three lesions were created, using various guidewires and power settings. Forty-one (95%) lesions were detected on cardiac magnetic resonance and 38 (88%) on necropsy; all undetected lesions resulted from intentionally subtherapeutic ablation energy (10 W). Larger-diameter guidewires yielded larger size lesions. Lesion volumes on necropsy were significantly larger at 20 W than 10 W (178 mm3 [Q1-Q3: 104-382 mm3] vs 49 mm3 [Q1-Q3: 35-93 mm3]; P = 0.02). Higher power (30 W) did not create larger lesions. Median impedance dropped with preablation irrigation by 12 Ω (Q1-Q3: 8-17 Ω), followed by a further 15-Ω (Q1-Q3: 11-19 Ω) drop during ablation. Intramyocardial navigation, ablation, and irrigation were not associated with any complications. CONCLUSIONS: VINTAGE was safe and effective at creating intramural ablation lesions in targets traditionally considered inaccessible from the endocardium and epicardium, both naive and infarcted. Intramyocardial guidewire irrigation and ablation at 20 W creates reproducibly large intramural lesions.

Validation of a machine learning algorithm to identify pulmonary vein isolation during ablation procedures for the treatment of atrial fibrillation: results of the PVISION study.

AIMS: Pulmonary vein isolation (PVI) is the cornerstone of ablation for atrial fibrillation. Confirmation of PVI can be challenging due to the presence of far-field electrograms (EGMs) and sometimes requires additional pacing manoeuvres or mapping. This prospective multicentre study assessed the agreement between a previously trained automated algorithm designed to determine vein isolation status with expert opinion in a real-world clinical setting. METHODS AND RESULTS: Consecutive patients scheduled for PVI were recruited at four centres. The ECGenius electrophysiology (EP) recording system (CathVision ApS, Copenhagen, Denmark) was connected in parallel with the existing system in the laboratory. Electrograms from a circular mapping catheter were annotated during sinus rhythm at baseline pre-ablation, time of isolation, and post-ablation. The ground truth for isolation status was based on operator opinion. The algorithm was applied to the collected PV signals off-line and compared with expert opinion. The primary endpoint was a sensitivity and specificity exceeding 80%. Overall, 498 EGMs (248 at baseline and 250 at PVI) with 5473 individual PV beats from 89 patients (32 females, 62 ± 12 years) were analysed. The algorithm performance reached an area under the curve (AUC) of 92% and met the primary study endpoint with a sensitivity and specificity of 86 and 87%, respectively (P = 0.005; P = 0.004). The algorithm had an accuracy rate of 87% in classifying the time of isolation. CONCLUSION: This study validated an automated algorithm using machine learning to assess the isolation status of pulmonary veins in patients undergoing PVI with different ablation modalities. The algorithm reached an AUC of 92%, with both sensitivity and specificity exceeding the primary study endpoints.

Use of three-dimensional electroanatomic mapping for epicardial access: needle tracking, electrographic characteristics, and clinical application.

AIMS: Pericardiocentesis is usually completed under fluoroscopy. The electroanatomic mapping (EAM) system allows visualizing puncture needle tip (NT) while displaying the electrogram recorded from NT, making it possible to obtain epicardial access (EA) independent of fluoroscopy. This study was designed to establish and validate a technique by which EA is obtained under guidance of three-dimensional (3D) EAM combined with NT electrogram. METHODS AND RESULTS: 3D shell of the heart was generated, and the NT was made trackable in the EAM system. Unipolar NT electrogram was continuously monitored. Penetration into pericardial sac was determined by an increase in NT potential amplitude and an injury current. A long guidewire of which the tip was also visible in the EAM system was advanced to confirm EA. Epicardial access was successfully obtained without complication in 13 pigs and 22 patients. In the animals, NT potential amplitude was 3.2 ± 1.0 mV when it was located in mediastinum, 5.2 ± 1.6 mV when in contact with fibrous pericardium, and 9.8 ± 2.8 mV after penetrating into pericardial sac (all P ≤ 0.001). In human subjects, it measured 1.54 ± 0.40 mV, 3.61 ± 1.08 mV, and 7.15 ± 2.88 mV, respectively (all P < 0.001). Fluoroscopy time decreased in every 4-5 cases (64 ± 15, 23 ± 17, and 0 s for animals 1-4, 5-8, 9-13, respectively, P = 0.01; 44 ± 23, 31 ± 18, 4±7 s for patients 1-7, 8-14, 15-22, respectively, P < 0.001). In five pigs and seven patients, EA was obtained without X-ray exposure. CONCLUSION: By tracking NT in the 3D EAM system and continuously monitoring the NT electrogram, it is feasible and safe to obtain EA with minimum or no fluoroscopic guidance.

Optimizing transseptal puncture guided by three-dimensional mapping: the role of a unipolar electrogram in a needle tip.

AIMS: A three-dimensional electroanatomic mapping system-guided transseptal puncture (3D-TSP), without fluoroscopy or echocardiography, has been only minimally reported. Indications for 3D-TSP remain unclear. Against this background, this study aims to establish a precise technique and create a workflow for validating and selecting eligible patients for fluoroless 3D-TSP. METHODS AND RESULTS: We developed a new methodology for 3D-TSP based on a unipolar electrogram derived from a transseptal needle tip (UEGM tip) in 102 patients (the derivation cohort) with intracardiac echocardiography (ICE) from March 2018 to February 2019. The apparent current of injury (COI) was recorded at the muscular limbus of the foramen ovalis (FO) on the UEGM tip (sinus rhythm: 2.57 ± 0.95 mV, atrial fibrillation: 1.92 ± 0.77 mV), which then disappeared or significantly reduced at the central FO. Changes in the COI, serving as a major criterion to establish a 3D-TSP workflow, proved to be the most valuable indicator for identifying the FO in 99% (101/102) of patients compared with three previous techniques (three minor criteria) of reduction in atrial unipolar or bipolar potential and FO protrusion. A total of 99.9% (1042/1043) patients in the validation cohort underwent successful 3D-TSP through the workflow from March 2019 to July 2023. Intracardiac echocardiography guidance was required for 6.6% (69/1042) of patients. All four criteria were met in 740 patients, resulting in a 100% pure fluoroless 3D-TSP success rate. CONCLUSION: In most patients, fluoroless 3D-TSP was successfully achieved using changes in the COI on the UEGM tip. Patients who met all four criteria were considered suitable for 3D-TSP, while those who met none required ICE guidance.

Understanding the Electrical Substrates Contributing to "Ablation-Resistant" Atrial Fibrillation?

Atrial fibrillation (AF) was largely ignored by cardiac electrophysiologists until it was first suggested in 1998 that it might be amenable to catheter ablation. In the 25 years since then, a vast body of knowledge has emerged, initially reporting the "hypes and hopes" that ablation was appropriate for all but more recently acknowledging that not all patients benefit from this approach. The AF "epidemic" and more holistic understanding of the complex contributors to its development question whether it is even meaningful to consider AF a single condition that is always responsive to ablation management. In this issue, Masuda et al11 provide novel insights into the electrophysiologic "footprints" that they found in the body of the left atrium of patients who underwent a second ablation procedure after achieving pulmonary vein isolation. In conclusion, the findings require prospective validation but may show a way of achieving antiarrhythmic success in a cohort of patients responding unpredictably to current ablation strategies.

Ventricular Tachycardia Ablation Endpoints: Moving Beyond Noninducibility.

In patients with structural heart disease and ventricular tachycardia (VT) undergoing catheter ablation, the response to programmed electrical stimulation (PES) at the end of the procedure has been traditionally used to evaluate the acute success and predict long-term outcomes. Although noninducibility at PES has been extensively investigated and validated in clinical trials and large multicenter registries, its performance in predicting long-term freedom from VT is suboptimal. In addition, PES has inherent limitations related to the influence of background antiarrhythmic drug therapy, periprocedural use of anesthesia, and the heterogeneity in PES protocols. The increased utilization of substrate-based ablation approaches that focus on ablation of abnormal electrograms identified with mapping in sinus or paced rhythm has been paralleled by a need for additional procedural endpoints beyond VT noninducibility at PES. This article critically appraises the relative merits and limitations of different procedural endpoints according to different ablation techniques for catheter ablation of scar-related VT.

Ebstein's anomaly: an electrophysiological perspective.

Ebstein's anomaly of the tricuspid valve (EA) is an uncommon congenital cardiac malformation. It can present with atrioventricular tachycardia (AVRT), atrioventricular nodal re-entrant tachycardia (AVNRT), atrial arrhythmias, and rarely with ventricular tachycardia. The 12-lead electrocardiogram (ECG) is critically important and often diagnostic even prior to an electrophysiology study (EPS). Due to its complex anatomy, it poses particular challenges for mapping and ablation, even for an experienced electrophysiologist. In this review, we aim to provide insight into the electrophysiological perspective of EA and an in-depth analysis of the various arrhythmias encountered in diverse clinical scenarios.

Optical mapping and optogenetics in cardiac electrophysiology research and therapy: a state-of-the-art review.

State-of-the-art innovations in optical cardiac electrophysiology are significantly enhancing cardiac research. A potential leap into patient care is now on the horizon. Optical mapping, using fluorescent probes and high-speed cameras, offers detailed insights into cardiac activity and arrhythmias by analysing electrical signals, calcium dynamics, and metabolism. Optogenetics utilizes light-sensitive ion channels and pumps to realize contactless, cell-selective cardiac actuation for modelling arrhythmia, restoring sinus rhythm, and probing complex cell-cell interactions. The merging of optogenetics and optical mapping techniques for 'all-optical' electrophysiology marks a significant step forward. This combination allows for the contactless actuation and sensing of cardiac electrophysiology, offering unprecedented spatial-temporal resolution and control. Recent studies have performed all-optical imaging ex vivo and achieved reliable optogenetic pacing in vivo, narrowing the gap for clinical use. Progress in optical electrophysiology continues at pace. Advances in motion tracking methods are removing the necessity of motion uncoupling, a key limitation of optical mapping. Innovations in optoelectronics, including miniaturized, biocompatible illumination and circuitry, are enabling the creation of implantable cardiac pacemakers and defibrillators with optoelectrical closed-loop systems. Computational modelling and machine learning are emerging as pivotal tools in enhancing optical techniques, offering new avenues for analysing complex data and optimizing therapeutic strategies. However, key challenges remain including opsin delivery, real-time data processing, longevity, and chronic effects of optoelectronic devices. This review provides a comprehensive overview of recent advances in optical mapping and optogenetics and outlines the promising future of optics in reshaping cardiac electrophysiology and therapeutic strategies.

Multisize Electrode Field-of-View: Validation by High Resolution Gadolinium-Enhanced Cardiac Magnetic Resonance.

BACKGROUND: Voltage mapping to detect ventricular scar is important for guiding catheter ablation, but the field-of-view of unipolar, bipolar, conventional, and microelectrodes as it relates to the extent of viable myocardium (VM) is not well defined. OBJECTIVES: The purpose of this study was to evaluate electroanatomic voltage-mapping (EAVM) with different-size electrodes for identifying VM, validated against high-resolution ex-vivo cardiac magnetic resonance (HR-LGE-CMR). METHODS: A total of 9 swine with early-reperfusion myocardial infarction were mapped with the QDOT microcatheter. HR-LGE-CMR (0.3-mm slices) were merged with EAVM. At each EAVM point, the underlying VM in multisize transmural cylinders and spheres was quantified from ex vivo CMR and related to unipolar and bipolar voltages recorded from conventional and microelectrodes. RESULTS: In each swine, 220 mapping points (Q1, Q3: 216, 260 mapping points) were collected. Infarcts were heterogeneous and nontransmural. Unipolar and bipolar voltage increased with VM volumes from >175 mm3 up to >525 mm3 (equivalent to a 5-mm radius cylinder with height >6.69 mm). VM volumes in subendocardial cylinders with 1- or 3-mm depth correlated poorly with all voltages. Unipolar voltages recorded with conventional and microelectrodes were similar (difference 0.17 ± 2.66 mV) and correlated best to VM within a sphere of radius 10 and 8 mm, respectively. Distance-weighting did not improve the correlation. CONCLUSIONS: Voltage increases with transmural volume of VM but correlates poorly with small amounts of VM, which limits EAVM in defining heterogeneous scar. Microelectrodes cannot distinguish thin from thick areas of subendocardial VM. The field-of-view for unipolar recordings for microelectrodes and conventional electrodes appears to be 8 to 10 mm, respectively, and unexpectedly similar.

Local VA index for the differential diagnosis of supraventricular tachycardia.

BACKGROUND: Differentiating between atypical atrioventricular nodal reentrant tachycardia (AVNRT) and orthodromic reciprocating tachycardia utilizing a septal accessory pathway is a complex challenge. OBJECTIVE: The purpose of this study was to describe the "local VA index," a straightforward method based on signals from the coronary sinus catheter, to distinguish between these arrhythmias during tachycardia and entrainment. The ventriculoatrial (VA) interval on the coronary sinus catheter is measured during tachycardia and entrainment, at the site of earliest atrial activity. The difference between these 2 situations defines the "local VA index." We also propose a mechanism to clarify the limitations of historical pacing maneuvers, such as postpacing interval minus tachycardia cycle length (PPI-TCL) and stimulus-atrial interval minus ventriculoatrial interval (SA-VA), by examining nodal decrement and intraventricular conduction delay. METHODS: In a retrospective study of 75 patients referred for supraventricular tachycardia evaluation, 37 were diagnosed with atrioventricular reentrant tachycardia (AVRT) with orthodromic reciprocating tachycardia, and 38 with AVNRT (27 typical, 11 atypical). RESULTS: In comparison to AVRT patients, AVNRT patients exhibited longer PPI-TCL (176 ± 47 ms vs 113 ± 42 ms; P <.01) and SA-VA (138 ± 47 ms vs 64 ± 28 ms; P <.01). The AVRT group had mean local VA index of -1 ± 13 ms, whereas the AVNRT group had a significantly longer index of 91 ± 46 ms (P <.01). An optimal threshold for differentiation was a local VA index of 40 ms. Importantly, there was no significant correlation between pacing cycle length and nodal decrement as well as intraventricular delay related to pathway location. This interindividual variability might explain misleading interpretations of PPI-TCL and SA-VA. CONCLUSION: This novel approach is advantageous because of its simplicity and effectiveness, requiring only 2 diagnostic catheters. A local VA interval difference <40 ms provides a clear distinction for AVRT.

Catheter ablation for non-paroxysmal atrial fibrillation. A review.

Atrial fibrillation (AF), the most common cardiac arrhythmia is associated with increased morbidity and mortality. The higher mortality is due to the risk of heart failure and cardioembolic events. This in-depth review focuses on the strategies and efficacy of catheter ablation for non-paroxysmal atrial fibrillation. The main medical databases were searched for contemporary studies on catheter ablation for non-paroxysmal AF. Catheter ablation is currently proven to be the most effective treatment for AF and consists of pulmonary vein isolation as the cornerstone plus additional ablations. In terms of SR maintenance, it is less effective in non-paroxysmal AF than in paroxysmal patients. but the clinical benefit in non-paroxysmal patients is substantially higher. Since pulmonary vein isolation is ineffective, a variety of techniques have been developed, e.g. linear ablations, ablation of complex atrial fractionated electrograms, etc. Another paradox consists in the technique of catheter ablation. Despite promising results in early observation studies, further randomized studies have not confirmed the initial enthusiasm. Recently, a new approach, pulsed-field ablation, appears promising. This is an in-depth summary of current technologies and techniques for the ablation of non-paroxysmal AF. We discuss the benefits, risks and implications in the treatment of patients with non-paroxysmal AF.

Image-Decomposition-Enhanced Deep Learning for Detection of Rotor Cores in Cardiac Fibrillation.

OBJECTIVE: Rotors, regions of spiral wave reentry in cardiac tissues, are considered as the drivers of atrial fibrillation (AF), the most common arrhythmia. Whereas physics-based approaches have been widely deployed to detect the rotors, in-depth knowledge in cardiac physiology and electrogram interpretation skills are typically needed. The recent leap forward in smart sensing, data acquisition, and Artificial Intelligence (AI) has offered an unprecedented opportunity to transform diagnosis and treatment in cardiac ailment, including AF. This study aims to develop an image-decomposition-enhanced deep learning framework for automatic identification of rotor cores on both simulation and optical mapping data. METHODS: We adopt the Ensemble Empirical Mode Decomposition algorithm (EEMD) to decompose the original image, and the most representative component is then fed into a You-Only-Look-Once (YOLO) object-detection architecture for rotor detection. Simulation data from a bi-domain simulation model and optical mapping acquired from isolated rabbit hearts are used for training and validation. RESULTS: This integrated EEMD-YOLO model achieves high accuracy on both simulation and optical mapping data (precision: 97.2%, 96.8%, recall: 93.8%, 92.2%, and F1 score: 95.5%, 94.4%, respectively). CONCLUSION: The proposed EEMD-YOLO yields comparable accuracy in rotor detection with the gold standard in literature.

Distributions and number of drivers on real-time phase mapping associated with successful atrial fibrillation termination during catheter ablation for non-paroxysmal atrial fibrillation.

BACKGROUND: Real-time phase mapping (ExTRa™) is useful in determining the strategy of catheter ablation for non-paroxysmal atrial fibrillation (AF). This study aimed to investigate the features of drivers of AF associated with its termination during ablation. METHODS: Thirty-six patients who underwent catheter ablation for non-paroxysmal AF using online real-time phase mapping (ExTRa™) were enrolled. A significant AF driver was defined as an area with a non-passively activated ratio of ≥ 50% on mapping analysis in the left atrium (LA). All drivers were simultaneously evaluated using a low-voltage area, complex fractionated atrial electrogram (CFAE), and rotational activity by unipolar electrogram analysis. The electrical characteristics of drivers were compared between patients with and without AF termination during the procedure. RESULTS: Twelve patients achieved AF termination during the procedure. The total number of drivers detected on the mapping was significantly lower (4.4 ± 1.6 vs. 7.4 ± 3.8, p = 0.007), and the drivers were more concentrated in limited LA regions (2.8 ± 0.9 vs. 3.9 ± 1.4, p = 0.009) in the termination group than in the non-termination group. The presence of drivers 2-6 with limited (≤ 3) LA regions showed a tenfold increase in the likelihood of AF termination, with 83% specificity and 67% sensitivity. Among 231 AF drivers, the drivers related to termination exhibited a greater overlap of CFAE (56.8 ± 34.1% vs. 39.5 ± 30.4%, p = 0.004) than the non-related drivers. The termination group showed a trend toward a lower recurrence rate after ablation (p = 0.163). CONCLUSIONS: Rotors responsible for AF maintenance may be characterized in cases with concentrated regions and fewer drivers on mapping.

Reliable focal and rotational activations in CARTOFINDER mapping using the OctaRay catheter.

INTRODUCTION: The aim of the current study was to elucidated the reliable atrial fibrillation (AF) drivers identified by CARTOFINDER using OctaRay catheter. METHODS AND RESULTS: The reliability of focal and rotational activations identified by CARTOFINDER using OctaRay catheter was assessed by the sequential recordings in each site of both atrium before and after pulmonary vein isolation (PVI) in 10 persistent AF patients. The outcome measures were the reproducibility rate during the sequential recordings and the stability rate between pre- and post-PVI as reliable focal and rotational activations. The study results were compared with those under use of PentaRay catheter (N = 18). Total 68928 points of 360 sites in OctaRay group and 24 177 points of 311 sites in PentaRay were assessed. More focal activation sites were identified in OctaRay group than PentaRay group (7.9% vs. 5.7%, p < .001), although the reproducibility rate and the stability rate were significantly lower in OctaRay group (45.3% vs. 58.9%, p < .001; 11.2% vs. 28.4%, p < .001). Meanwhile, the prevalence of reproducible focal activation sites among overall points was comparable (3.6% vs. 3.3%, p = .08). Regarding rotational activation, more rotational activation sites were identified in OctaRay group (5.1% vs. 0.2%, p < .001), and the reproducibility rate and the stability rate were significantly higher in OctaRay group (45.2% and 12.5% vs. 0.0%, p < .001). Both reliable focal and rotational activation sites were characterized by significantly shorter AF-cycle length (CL) and higher repetition of focal and rotational activations during the recordings compared with the sites of non or unreliable focal and rotational activations. CONCLUSION: In CARTOFINDER, OctaRay catheter could identify reliable focal activation with high resolution and reliable rotational activation compared with PentaRay catheter. The repetitive focal and rotational activations with short AF-CL could be the potential target during ablation.

Assessment of the Interelectrode Distance Effect over the Omnipole with High Multielectrode Arrays.

The development of high-density multielectrode catheters has significantly advanced cardiac electrophysiology mapping. High-density grid catheters have enabled the creation of a novel technique for reconstructing electrogram (EGM) signals known as "omnipole," which is believed to be more reliable than other methods, especially in terms of orientation independence. This study aims to evaluate how distance affects the omnipolar reconstruction of EGMs by comparing different configurations. Using an animal set up of perfused isolated rabbit hearts, recordings were taken using an ad hoc high-density epicardial multielectrode catheter. Inter-electrode distances ranging from 1 to 4 mm were analysed for their effect on the quality of resulting EGMs. Two biomarkers were computed to evaluate the robustness of the reconstructions: the areas contained within the bipolar loops and the amplitudes of the omnipoles. We hypothesised that both bipolar and omnipolar electrograms would be more robust at shorter inter-electrode distances. The results showed that an increase in distance triggers an increase in loop areas and amplitudes, which supports the hypothesis. This finding provides a more reliable estimate of wavefront propagation for the cross-omnipolar reconstruction method. These results emphasise the importance of distance in cardiac electrophysiology mapping and provide valuable insights into the use of high-density multielectrode catheters for EGM reconstruction.Clinical Relevance- The results of this study have direct clinical relevance in the application of the described techniques to recording systems in the cardiac electrophysiology laboratory, enabling clinicians to obtain more precise characterisation of signals in the myocardium.