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.

Promises and Perils of Consumer Mobile Technologies in Cardiovascular Care: JACC Scientific Statement.

Direct-to-consumer (D2C) wearables are becoming increasingly popular in cardiovascular health management because of their affordability and capability to capture diverse health data. Wearables may enable continuous health care provider-patient partnerships and reduce the volume of episodic clinic-based care (thereby reducing health care costs). However, challenges arise from the unregulated use of these devices, including questionable data reliability, potential misinterpretation of information, unintended psychological impacts, and an influx of clinically nonactionable data that may overburden the health care system. Further, these technologies could exacerbate, rather than mitigate, health disparities. Experience with wearables in atrial fibrillation underscores these challenges. The prevalent use of D2C wearables necessitates a collaborative approach among stakeholders to ensure effective integration into cardiovascular care. Wearables are heralding innovative disease screening, diagnosis, and management paradigms, expanding therapeutic avenues, and anchoring personalized medicine.

A Comprehensive Comparison of Six Publicly Available Algorithms for Localization of QRS Complex on Electrocardiograph.

The QRS complex is the most prominent feature of the electrocardiogram (ECG) that is used as a marker to identify the cardiac cycles. Identification of QRS complex locations enables arrhythmia detection and heart rate variability estimation. Therefore, accurate and consistent localization of the QRS complex is an important component of automated ECG analysis which is necessary for the early detection of cardiovascular diseases. This study evaluates the performance of six popular publicly available QRS complex detection methods on a large dataset of over half a million ECGs in a diverse population of patients. We found that a deep-learning method that won first place in the 2019 Chinese physiological challenge (CPSC-1) outperforms the remaining five QRS complex detection methods with an F1 score of 98.8% and an absolute sdRR error of 5.5 ms. We also examined the stratified performance of the studied methods on various cardiac conditions. All six methods had a lower performance in the detection of QRS complexes in ECG signals of patients with pacemakers, complete atrioventricular block, or indeterminate cardiac axis. We also concluded that, in the presence of different cardiac conditions, CPSC-1 is more robust than Pan-Tompkins which is the most popular model for QRS complex detection. We expect that this study can potentially serve as a guide for researchers on the appropriate QRS detection method for their target applications.Clinical Relevance-This study highlights the overall performance of publicly available QRS detection algorithms in a large dataset of diverse patients. We showed that there are specific cardiac conditions that are associated with the poor performance of QRS detection algorithms and may adversely influence the performance of algorithms that rely on accurate and reliable QRS detection.

Multi-center atrial fibrillation electrocardiogram (ECG) classification using Fourier space convolutional neural networks (FD-CNN) and transfer learning.

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching >85% accuracy for various cardiac pathologies. Despite the high accuracy at individual institutions, challenges remain when it comes to multi-center deployment. Transfer learning (TL) is a technique in which a model trained for a specific task is repurposed for another related task, in this case ECG ML model trained at one institution is fine-tuned to be utilized to classify ECGs at another institution. Models trained at one institution, however, might not be generalizable for accurate classification when deployed broadly due to differences in type, time, and sampling rate of traditional ECG acquisition. In this study, we evaluate the performance of time domain (TD) and frequency domain (FD) convolutional neural network (CNN) classification models in an inter-institutional scenario leveraging three different publicly available datasets. The larger PTB-XL ECG dataset was used to initially train TD and FD CNN models for atrial fibrillation (AFIB) classification. The models were then tested on two different data sets, Lobachevsky University Electrocardiography Database (LUDB) and Korea University Medical Center database (KURIAS). The FD model was able to retain most of its performance (>0.81 F1-score), whereas TD was highly affected (<0.53 F1-score) by the dataset variations, even with TL applied. The FD CNN showed superior robustness to cross-institutional variability and has potential for widespread application with no compromise to ECG classification performance.

Episodes of Atrial Fibrillation and Symptoms: A Temporal Analysis.

Background: Data on the relationship between symptoms and atrial fibrillation (AF) episodes are limited. Objective: The objective of this study was to determine the strength of temporal association between AF episodes and symptoms. Methods: This cross-sectional ambulatory assessment study was performed in a tertiary care center between June 2018 and December 2021. Patients with paroxysmal AF (1 episode of AF, burden not exceeding 95%) who used a mobile application and continuous wearable electrocardiogram monitor for 21 days were enrolled. The primary outcome was worse symptoms (symptoms above the mean score) over the study period. The association between worse symptoms and the presence of AF was evaluated for different time epochs. Multilevel mixed-effects models were used to quantify associations after accounting for confounders. Results: Worse symptoms were more likely to be associated with the presence of AF episodes 15 minutes prior to the reporting of palpitations (OR, 2.8 [95% CI, 1.6-5.0]; P < .001), shortness of breath (OR, 2.2 [95% CI, 1.3-3.7]; P = .003), dizziness/lightheadedness (OR, 2.0 [95% CI, 1.0-3.7]; P = .04), and fatigue (OR, 1.7 [95% CI, 1.0-2.9]; P = .03). The correlation between the severity of symptoms and AF lessened as the time interval from AF events to symptoms increased. Conclusion: There is a significant relationship between onset of AF episodes and reporting of symptoms. This association diminishes over time and varies across different symptoms. If confirmed in larger studies, these findings may inform AF interventions that target symptoms just in time prior to a clinical visit.

Validation of a Deep Learning Algorithm for Continuous, Real-Time Detection of Atrial Fibrillation Using a Wrist-Worn Device in an Ambulatory Environment.

BACKGROUND: Wearable devices may be useful for identification, quantification and characterization, and management of atrial fibrillation (AF). To date, consumer wrist-worn devices for AF detection using photoplethysmography-based algorithms perform only periodic checks when the user is stationary and are US Food and Drug Administration cleared for prediagnostic uses without intended use for clinical decision-making. There is an unmet need for medical-grade diagnostic wrist-worn devices that provide long-term, continuous AF monitoring. METHODS AND RESULTS: We evaluated the performance of a wrist-worn device with lead-I ECG and continuous photoplethysmography (Verily Study Watch) and photoplethysmography-based convolutional neural network for AF detection and burden estimation in a prospective multicenter study that enrolled 117 patients with paroxysmal AF. A 14-day continuous ECG monitor (Zio XT) served as the reference device to evaluate algorithm sensitivity and specificity for detection of AF in 15-minute intervals. A total of 91 857 intervals were contributed by 111 subjects with evaluable reference and test data (18.3 h/d median watch wear time). The watch was 96.1% sensitive (95% CI, 92.7%-98.0%) and 98.1% specific (95% CI, 97.2%-99.1%) for interval-level AF detection. Photoplethysmography-derived AF burden estimation was highly correlated with the reference device burden (R2=0.986) with a mean difference of 0.8% (95% limits of agreement, -6.6% to 8.2%). CONCLUSIONS: Continuous monitoring using a photoplethysmography-based convolutional neural network incorporated in a wrist-worn device has clinical-grade performance for AF detection and burden estimation. These findings suggest that monitoring can be performed with wrist-worn wearables for diagnosis and clinical management of AF. REGISTRATION INFORMATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04546763.

Fourier space approach for convolutional neural network (CNN) electrocardiogram (ECG) classification: A proof-of-concept study.

There has been a proliferation of machine learning (ML) electrocardiogram (ECG) classification algorithms reaching > 85% accuracy for various cardiac pathologies. Although the accuracy within institutions might be high, models trained at one institution might not be generalizable enough for accurate detection when deployed in other institutions due to differences in type of signal acquisition, sampling frequency, time of acquisition, device noise characteristics and number of leads. In this proof-of-concept study, we leverage the publicly available PTB-XL dataset to investigate the use of time-domain (TD) and frequency-domain (FD) convolutional neural networks (CNN) to detect myocardial infarction (MI), ST/T-wave changes (STTC), atrial fibrillation (AFIB) and sinus arrhythmia (SARRH). To simulate interinstitutional deployment, the TD and FD implementations were also compared on adapted test sets using different sampling frequencies 50 Hz, 100 Hz and 250 Hz, and acquisition times of 5 s and 10s at 100 Hz sampling frequency from the training dataset. When tested on the original sampling frequency and duration, the FD approach showed comparable results to TD for MI (0.92 FD - 0.93 TD AUROC) and STTC (0.94 FD - 0.95 TD AUROC), and better performance for AFIB (0.99 FD - 0.86 TD AUROC) and SARRH (0.91 FD - 0.65 TD AUROC). Although both methods were robust to changes in sampling frequency, changes in acquisition time were detrimental to the TD MI and STTC AUROCs, at 0.72 and 0.58 respectively. Alternatively, the FD approach was able to maintain the same level of performance, and, therefore, showed better potential for interinstitutional deployment.

Three-dimensional-guided and ICE-guided transseptal puncture for cardiac ablations: A propensity score match study.

INTRODUCTION: Transseptal puncture (TSP) is routinely performed for left atrial ablation procedures. The use of a three-dimensional (3D) mapping system or intracardiac echocardiography (ICE) is useful in localizing the fossa ovalis and reducing fluoroscopy use. We aimed to compare the safety and efficacy between 3D mapping system-guided TSP and ICE-guided TSP techniques. METHODS: We conducted a prospective observational study of patients undergoing TSP for left atrial catheter ablation procedures (mostly atrial fibrillation ablation). Propensity scoring was used to match patients undergoing 3D-guided TSP with patients undergoing ICE-guided TSP. Logistic regression was used to compare the clinical data, procedural data, fluoroscopy time, success rate, and complications between the groups. RESULTS: Sixty-five patients underwent 3D-guided TSP, and 151 propensity score-matched patients underwent ICE-guided TSP. The TSP success rate was 100% in both the 3D-guided and ICE-guided groups. Median needle time was 4.00 min (interquartile range [IQR]: 2.57-5.08) in patients with 3D-guided TSP compared to 4.02 min (IQR: 2.83-6.95) in those with ICE-guided TSP (p = .22). Mean fluoroscopy time was 0.2 min (IQR: 0.1-0.4) in patients with 3D-guided TSP compared to 1.2 min (IQR: 0.7-2.2) in those with ICE-guided TSP (p < .001). There were no complications related to TSP in both group. CONCLUSIONS: Three-dimensional mapping-guided TSP is as safe and effective as ICE-guided TSP without additional cost.

Issues in the automated classification of multilead ecgs using heterogeneous labels and populations.

Objective.The standard twelve-lead electrocardiogram (ECG) is a widely used tool for monitoring cardiac function and diagnosing cardiac disorders. The development of smaller, lower-cost, and easier-to-use ECG devices may improve access to cardiac care in lower-resource environments, but the diagnostic potential of these devices is unclear. This work explores these issues through a public competition: the 2021 PhysioNet Challenge. In addition, we explore the potential for performance boosting through a meta-learning approach.Approach.We sourced 131,149 twelve-lead ECG recordings from ten international sources. We posted 88,253 annotated recordings as public training data and withheld the remaining recordings as hidden validation and test data. We challenged teams to submit containerized, open-source algorithms for diagnosing cardiac abnormalities using various ECG lead combinations, including the code for training their algorithms. We designed and scored the algorithms using an evaluation metric that captures the risks of different misdiagnoses for 30 conditions. After the Challenge, we implemented a semi-consensus voting model on all working algorithms.Main results.A total of 68 teams submitted 1,056 algorithms during the Challenge, providing a variety of automated approaches from both academia and industry. The performance differences across the different lead combinations were smaller than the performance differences across the different test databases, showing that generalizability posed a larger challenge to the algorithms than the choice of ECG leads. A voting model improved performance by 3.5%.Significance.The use of different ECG lead combinations allowed us to assess the diagnostic potential of reduced-lead ECG recordings, and the use of different data sources allowed us to assess the generalizability of the algorithms to diverse institutions and populations. The submission of working, open-source code for both training and testing and the use of a novel evaluation metric improved the reproducibility, generalizability, and applicability of the research conducted during the Challenge.

A comparison of clinical outcomes and cost of radiofrequency catheter ablation for atrial fibrillation with monitored anesthesia care versus general anesthesia.

INTRODUCTION: Monitored anesthesia care (MAC) or general anesthesia (GA) can be used during catheter ablation (CA) of atrial fibrillation (AF). However, each approach may have advantages and disadvantages with variability in operator preferences. The optimal approach has not been well established. The purpose of this study was to compare procedural efficacy, safety, clinical outcomes, and cost of CA for AF performed with MAC versus GA. METHODS: The study population consisted of 810 consecutive patients (mean age: 63 ± 10 years, paroxysmal AF: 48%) who underwent a first CA for AF. All patients completed a preprocedural evaluation by the anesthesiologists. Among the 810 patients, MAC was used in 534 (66%) and GA in 276 (34%). Ten patients (1.5%) had to convert to GA during the CA. RESULTS: Although the total anesthesia care was longer with GA particularly in patients with persistent AF, CA was shorter by 5 min with GA than MAC (p < 0.01). Prevalence of perioperative complications was similar between the two groups (4% vs. 4%, p = 0.89). There was no atrioesophageal fistula with either approach. GA was associated with a small, ~7% increase in total charges due to longer anesthesia care. During 43 ± 17 months of follow-up after a single ablation procedure, 271/534 patients (51%) in the MAC and 129/276 (47%) patients in the GA groups were in sinus rhythm without concomitant antiarrhythmic drug therapy (p = 0.28). CONCLUSION: With the participation of an anesthesiologist, and proper preoperative assessment, CA of AF using GA or MAC has similar efficacy and safety.

Clinical characteristics and long-term outcomes of catheter ablation in young adults with atrial fibrillation.

PURPOSE: We aim to describe the long-term safety and efficacy of catheter ablation (CA) in young patients (<30 years) with atrial fibrillation (AF). METHODS: This was a retrospective study of patients aged 18-30 who underwent CA for AF, and clinical characteristics and long-term outcomes are reported. Survival analyses were performed between the study group and a propensity-matched older cohort (>30 years, mean age: 58±10 years). RESULTS: From January 2000 to January 2019, a 1st CA (radiofrequency energy n=72, cryoballoon n=10), was performed in 82 patients (mean age 26±4 years, paroxysmal n=61, persistent n=14, longstanding persistent n=7), among 6336 consecutive patients with AF. During a follow-up of 5±5 years, 56% and 30% of the patients with paroxysmal and non-paroxysmal AF were arrhythmia free without antiarrhythmic drug (AAD) therapy after a single CA (P=0.02). After 1.5±0.8 CA procedures, 76% and 75% of the patients with paroxysmal AF and non-paroxysmal AF were arrhythmia free without AADs (P=0.54). Compared to a propensity-matched group of older patients, young patients were as likely to remain in sinus rhythm after CA (P=0.47), however after fewer repeat CAs (1.5±0.8 vs 1.9±0.9, P<0.009). There were no long-term adverse outcomes associated with CA. CONCLUSIONS: CA is a safe and effective treatment of AF in young patients with comparable outcomes to the older patients, however after fewer procedures.

Predicting atrial fibrillation episodes with rapid ventricular rates associated with low levels of activity.

BACKGROUND: Rapid and irregular ventricular rates (RVR) are an important consequence of atrial fibrillation (AF). Raw accelerometry data in combination with electrocardiogram (ECG) data have the potential to distinguish inappropriate from appropriate tachycardia in AF. This can allow for the development of a just-in-time intervention for clinical treatments of AF events. The objective of this study is to develop a machine learning algorithm that can distinguish episodes of AF with RVR that are associated with low levels of activity. METHODS: This study involves 45 patients with persistent or paroxysmal AF. The ECG and accelerometer data were recorded continuously for up to 3 weeks. The prediction of AF episodes with RVR and low activity was achieved using a deterministic probabilistic finite-state automata (DPFA)-based approach. Rapid and irregular ventricular rate (RVR) is defined as having heart rates (HR) greater than 110 beats per minute (BPM) and high activity is defined as greater than 0.75 quantile of the activity level. The AF events were annotated using the FDA-cleared BeatLogic algorithm. Various time intervals prior to the events were used to determine the longest prediction intervals for predicting AF with RVR episodes associated with low levels of activity. RESULTS: Among the 961 annotated AF events, 292 met the criterion for RVR episode. There were 176 and 116 episodes with low and high activity levels respectively. Out of the 961 AF episodes, 770 (80.1%) were used in the training data set and the remaining 191 intervals were held out for testing. The model was able to predict AF with RVR and low activity up to 4.5 min before the events. The mean prediction performance gradually decreased as the time to events increased. The overall Area under the ROC Curve (AUC) for the model lies within the range of 0.67-0.78. CONCLUSION: The DPFA algorithm can predict AF with RVR associated with low levels of activity up to 4.5 min before the onset of the event. This would enable the development of just-in-time interventions that could reduce the morbidity and mortality associated with AF and other similar arrhythmias.

A Patient-Centered Design Thinking Workshop to Improve Patient-Provider Communication in Cardiovascular Medicine.

Healthcare providers are expected to deliver care improvement solutions that not only provide high quality patient care, but also improve outcomes, reduce costs, ensure safety, and increase patient satisfaction. Human-centered design methodologies, such as design thinking, allow providers to collaboratively ideate solutions with patients and family members. We describe a pilot workshop designed to teach providers the stages of design thinking while working on improving patient-provider communication. Twenty-four providers (physicians, nurses, technical staff, and administrative staff) from multiple cardiovascular units attended the workshop with five former patients and family members from those units. The workshop educated on and guided teams of providers patients and family members through the stages of design thinking (empathy, define, ideate, prototype, test). Pre- and post-event assessments indicated an increase in knowledge of the design thinking methodology and participants' ability to apply it to a clinical problem. We also present recommendations for designing a successful design thinking workshop.

Efficacy and tolerability of quinidine as salvage therapy for monomorphic ventricular tachycardia in patients with structural heart disease.

INTRODUCTION: Quinidine is an effective therapy for a subset of polymorphic ventricular tachycardia and ventricular fibrillation (VF) syndromes; however, the efficacy of quinidine in scar-related monomorphic ventricular tachycardia (MMVT) is unclear. METHODS AND RESULTS: Between 2009 and 2020 a single VT referral center, a total of 23 patients with MMVT and structural heart disease (age 66.7 ± 10.9, 20 males, 15 with ischemic cardiomyopathy, mean LVEF 22.2 ± 12.3%, 9 with left ventricular assist device [LVAD]) were treated with quinidine (14 quinidine gluconate; 996 ± 321 mg, 8 quinidine sulfate; 1062 ± 588 mg). Quinidine was used in combination with other antiarrhythmics (AAD) in 19 (13 also on amiodarone). All patients previously failed >1 AAD (amiodarone 100%, mexiletine 73%, sotalol 32%, other 32%) and eight had prior ablations (median of 1.5). Quinidine was initiated in the setting of VT storm despite AADs (6), inability to tolerate other AADs (4), or recurrent VT(12). Ventricular arrhythmias recurred despite quinidine in 13 (59%) patients at a median of 26 (4-240) days after quinidine initiation. In patients with recurrent MMVT, VT cycle length increased from 359 to 434 ms (p = .02). Six (27.3%) patients remained on quinidine at 1 year with recurrence of ventricular arrhythmias in all. The following adverse effects were seen: gastrointestinal side effects (6), QT prolongation (2), rash (1), thrombocytopenia (1), neurologic side effects (1). One patient discontinued due to cost. CONCLUSION: Quinidine therapy has limited tolerability and long-term efficacy when used in the management of amiodarone-refractory scar-related MMVT.