Jagmeet P. Singh

Cardiac Implantable Electronic Devices (CIEDs), ranging from Permanent Pacemakers (PPMs) for bradycardia, Implantable Cardioverter-Defibrillators (ICDs), to Cardiac Resynchronization Therapy (CRT) with Pacing (CRT-P) or Defibrillation (CRT-D), have been shown to significantly improve morbidity and mortality across a variety of clinical scenarios. The burden of cardiovascular disease and the indications for CIED implantation increase with age. These trends are becoming increasingly apparent with rising life expectancy, necessitating evidencebased therapeutic interventions for older adult patients. However, older adults, particularly those aged ≥75 years, were either markedly underrepresented or excluded from major Randomized Controlled Trials (RCTs) evaluating CIED, in which the mean participant age was predominantly in the 60s. Consequently, there has been a tendency to extrapolate the findings of these trials in subsequent guideline recommendations and consensus statements to older adults despite the lack of clear, adequately tested evidence regarding the benefits and risks of such recommendations in this population. As a result, real-world observational studies, in which older adults are often overrepresented, have largely been relied upon to characterize the efficacy and safety of CIED implantation. Complications associated with CIED implantation and long-term outcomes are generally worse in older adults than in younger patients, particularly among those with premature biological aging, increased frailty, and/or a high burden of comorbidities. Nevertheless, uncertainty remains regarding the balance of benefits and risks associated with certain invasive cardiac device therapies in older adults. This narrative review critically summarizes the current evidence regarding the efficacy and safety of CIEDs in adults aged ≥75 years compared with those aged <75 years.

Aims: Artificial intelligence (AI)-enabled electrocardiograms (AI-ECG) can detect left ventricular systolic dysfunction (LVSD), but demographic imbalance in training datasets may introduce bias. Foundational models, pretrained on large and diverse datasets, may mitigate such concerns. We aimed to assess the impact of demographic composition in training datasets on the performance of an ECG Foundational Model (ECGFM) for diagnosing LVSD. Methods and results: We developed an ECG foundational model (ECGFM) using transformer architecture and self-supervised pretraining on 983 200 ECGs. Using 44 815 paired ECG–echocardiogram datasets, we trained the model under three biased scenarios: (1) sex-skewed (male-only or female-only), (2) race-skewed (White-only or non-White), and (3) balanced. Models were evaluated on a test cohort consisting of 4663 male patients (52%) and 4300 female patients (48%) for the sex configuration and 4440 (49.5%) White, 558 (6.2%) Black, 925 Asian (10.3%), and 3040 other (33.9%) patients, for the race-based configuration using area under the receiver operating characteristic curve (AUROC). The ECGFM demonstrated consistent performance across all demographic configurations. Training on male-only or female-only cohorts yielded comparable AUROC scores of 0.85–0.90 for both sexes in the test set in predicting LVSD. Similarly, training on White-only or non-White cohorts resulted in robust AUROC scores (≥0.90) across all racial groups, including Asian, Black, Hispanic/Latino, and American Indian/Native Alaskan subgroups. Balanced and imbalanced training produced comparable accuracy, sensitivity, and specificity. The performance of the model was externally tested in EchoNext, revealing AUROC scores 0.823–0.917 for sex and 0.822–0.917 for race. Conclusion: Our transformer-based ECG foundational model pretrained using self-supervised learning demonstrated preserved diagnostic accuracy for LVSD across diverse demographic groups, even when trained on demographically imbalanced datasets.

Background: This retrospective observational study compared adverse events (AEs) and health care resource use among patients with atrial fibrillation treated with dronedarone versus amiodarone. Methods: Adults with atrial fibrillation who initiated dronedarone or amiodarone between January 1, 2010 and September 30, 2021 were propensity score matched in Optum’s deidentified Clinformatics Data Mart Database. Outcomes included AEs (described in the dronedarone/amiodarone Food and Drug Administration labels and reported in the Food and Drug Administration AE Reporting System) and all‐cause and cardiovascular‐related health care resource use. Generalized linear models with Poisson distribution were used to compare the risk of AEs between the 2 cohorts. After matching, 12 210 dronedarone‐treated patients were paired 1:1 with amiodarone‐treated patients. For each AE, patients who experienced the AE during baseline were excluded. Results: During follow‐up, lower event rates of AEs were observed with dronedarone versus amiodarone; the rate ratio for any cardiac and vascular AE was 0.71 (95% CI, 0.69–0.72), any respiratory AE was 0.65 (95% CI, 0.63–0.66), and any gastrointestinal/hepatobiliary AE was 0.81 (95% CI, 0.79–0.84). Compared with amiodarone‐treated patients, dronedarone‐treated patients experienced lower event rates of all‐cause hospitalization (0.69 [95% CI, 0.67–0.71]) and all‐cause outpatient visits (0.87 [95% CI, 0.87–0.87]). Although the incidence of cardiovascular‐related hospitalization was higher with dronedarone versus amiodarone, event rates were not statistically different. Cardiovascular‐related outpatient visits were significantly reduced with dronedarone versus amiodarone with an event rate of 0.95 (95% CI, 0.94–0.96). Conclusions: In this study, lower event/incidence rates of AEs and health care resource use were observed in patients with atrial fibrillation treated with dronedarone versus amiodarone.

BACKGROUND: Bradyarrhythmia is a common and potentially serious cause of syncope, often difficult to detect due to its intermittent nature. Traditional ECG monitoring methods either provide low diagnostic accuracy or delay diagnosis, increasing the risk of recurrence. We hypothesized that a deep learning–enabled, 24-hour, single-lead ECG could detect past episodes of bradyarrhythmia. METHODS: Using unselected 14-day single-lead ambulatory ECG recordings, we developed a deep learning model to identify patients with prior asystole from sinus arrest or complete heart block. The model was trained using the last 24 hours of each recording, free of bradyarrhythmias, to identify daytime sinus pause of ≥3 s, anytime sinus pause of ≥6 s, complete heart block, or a composite of these bradyarrhythmias from the previous 13 days. RESULTS: A total of 320 959 unselected 14-day ambulatory ECG recordings (mean age, 60.5±17.8 years; 60% female) were split into training (n=189 414), tuning (n=45 982), internal validation (n=43 390), and external validation (n=42 173) sets. External validation of prior daytime sinus pause ≥3 s, anytime sinus pause ≥6 s, complete heart block, and a composite end point demonstrated an area under the receiver operating characteristic curve of 0.89, 0.87, 0.93, and 0.89, respectively, with negative predictive values between 97.9 and 99.9%. In addition to this approach of uncovering past events, our model was also tested for its ability to predict bradyarrhythmias within the following 13 days using the first 24 hours of ECG data, achieving an AUC of 0.88 for the composite end point. CONCLUSIONS: A deep learning–enabled ambulatory ECG is capable of unmasking underlying conduction tissue system disease. This tool may help identify patients with significant intermittent bradyarrhythmia, potentially improving timely diagnosis and management.

BACKGROUND: The CommandEP system v2 (Sentiar, St. Louis, MO) utilizes an augmented reality headset (Magic Leap, Plantation, FL) to display a real-time 3-dimensional electroanatomic map, catheter locations, and ablation catheter contact force data to the electrophysiologist using a hands-free interface. In the intra-PARADIGM study (Procedural Augmented Reality Assessment in a 3-Dimensional Image Guided Modality), the impact of the CommandEP system on the electrophysiologist’s ability to navigate accurately, intraprocedural communications, and system usability were studied. METHODS: CommandEP was used prospectively in patients undergoing electrophysiologist studies at 2 sites with 8 users. The electrophysiologist’s ability to navigate accurately was calculated as catheter tip displacement from the target using CommandEP versus the electroanatomic mapping system. Physician-mapper interactions were quantified and classified as high- versus low-quality communications (high quality directly impacted navigation, medical decision-making, or patient care). Usability was assessed via survey. RESULTS: A total of 102 patients completed the study with the following diagnoses: atrial fibrillation (n=78/102, 76%), atrial flutter (8/102, 8%), atrial tachycardia/supraventricular tachycardia (n=9/102, 9%), premature ventricular contraction (n=6/102, 6%), and cardiac neuroablation (1/102, 1%). The physician’s ability to navigate was more accurate when using the CommandEP system with an average distance of 2.98±2 mm versus electroanatomic mapping system 3.27±2 mm ( P =0.02); 21% of points navigated using CommandEP versus 28% of points navigated using electroanatomic mapping system were >4 mm from the target ( P =0.03). In all, 393 communications during study tasks were counted with 30 events when using CommandEP versus 363 events when using electroanatomic mapping system. Subanalysis showed no difference in accuracy pre- versus postcontact force (p=ns) and a slight reduction in both low- and high-quality communications (p=ns). Notably, 94% agreed/strongly agreed that they felt comfortable using the system, and 72% agreed/strongly agreed they would be comfortable using the CommandEP system in most/all EPS. CONCLUSIONS: The CommandEP system improved physicians’ ability to navigate accuracy, reduced the number of communications, increased the quality of communications, and had high usability.

Aims: Artificial intelligence (AI) has the potential to transform cardiac electrophysiology (EP), particularly in arrhythmia detection, procedural optimization, and patient outcome prediction. However, a standardized approach to reporting and understanding AI-related research in EP is lacking. This scientific statement aims to develop and apply a checklist for AI-related research reporting in EP to enhance transparency, reproducibility, and understandability in the field. Methods and results: An AI checklist specific to EP was developed with expert input from the writing group and voted on using a modified Delphi process, leading to the development of a 29-item checklist. The checklist was subsequently applied to assess reporting practices to identify areas where improvements could be made and provide an overview of the state of the art in AI-related EP research in three domains from May 2021 until May 2024: atrial fibrillation (AF) management, sudden cardiac death (SCD), and EP lab applications. The EHRA AI checklist was applied to 31 studies in AF management, 18 studies in SCD, and 6 studies in EP lab applications. Results differed between the different domains, but in no domain reporting of a specific item exceeded 55% of included papers. Key areas such as trial registration, participant details, data handling, and training performance were underreported (<20%). The checklist application highlighted areas where reporting practices could be improved to promote clearer, more comprehensive AI research in EP. Conclusion: The EHRA AI checklist provides a structured framework for reporting AI research in EP. Its use can improve understanding but also enhance the reproducibility and transparency of AI studies, fostering more robust and reliable integration of AI into clinical EP practice.