An electrocardiogram-based AI algorithm for early detection of pulmonary hypertension.

BACKGROUND: Early diagnosis of pulmonary hypertension (PH) is critical for effective treatment and management. We aimed to develop and externally validate an artificial intelligence algorithm that could serve as a PH screening tool, based on analysis of a standard 12-lead electrocardiogram (ECG). METHODS: The PH Early Detection Algorithm (PH-EDA) is a convolutional neural network developed using retrospective ECG voltage-time data, with patients classified as "PH-likely" or "PH-unlikely" (controls) based on right heart catheterisation or echocardiography. In total, 39 823 PH-likely patients and 219 404 control patients from Mayo Clinic were randomly split into training (48%), validation (12%), and test (40%) sets. ECGs taken within 1 month of PH diagnosis (diagnostic dataset) were used to train the PH-EDA at Mayo Clinic. Performance was tested on diagnostic ECGs within the test sets from Mayo Clinic (n=16 175/87 998 PH-likely/controls) and Vanderbilt University Medical Center (VUMC; n=6045/24 256 PH-likely/controls). Performance was also tested on ECGs taken 6-18 months (pre-emptive dataset), and up to 5 years prior to a PH diagnosis at both sites. RESULTS: Performance testing yielded an area under the receiver operating characteristic curve (AUC) of 0.92 and 0.88 in the diagnostic test set at Mayo Clinic and VUMC, respectively, and 0.86 and 0.81, respectively, in the pre-emptive test set. The AUC remained a minimum of 0.79 at Mayo Clinic and 0.73 at VUMC up to 5 years before diagnosis. CONCLUSION: The PH-EDA can detect PH at diagnosis and 6-18 months prior, demonstrating the potential to accelerate diagnosis and management of this debilitating disease.

Realtime Diagnosis from Electrocardiogram Artificial Intelligence-Guided Screening for Atrial Fibrillation with Long Follow-Up (REGAL): Rationale and design of a pragmatic, decentralized, randomized controlled trial.

BACKGROUND: Atrial fibrillation (AF) is associated with increased risks of stroke and dementia. Early diagnosis and treatment could reduce the disease burden, but AF is often undiagnosed. An artificial intelligence (AI) algorithm has been shown to identify patients with previously unrecognized AF; however, monitoring these high-risk patients has been challenging. Consumer wearable devices could be an alternative to enable long-term follow-up. OBJECTIVES: To test whether Apple Watch, used as a long-term monitoring device, can enable early diagnosis of AF in patients who were identified as having high risk based on AI-ECG. DESIGN: The Realtime diagnosis from Electrocardiogram (ECG) Artificial Intelligence (AI)-Guided Screening for Atrial Fibrillation (AF) with Long Follow-up (REGAL) study is a pragmatic trial that will accrue up to 2,000 older adults with a high likelihood of unrecognized AF determined by AI-ECG to reach our target of 1,420 completed participants. Participants will be 1:1 randomized to intervention or control and will be followed up for 2 years. Patients in the intervention arm will receive or use their existing Apple Watch and iPhone and record a 30-second ECG using the watch routinely or if an abnormal heart rate notification is prompted. The primary outcome is newly diagnosed AF. Secondary outcomes include changes in cognitive function, stroke, major bleeding, and all-cause mortality. The trial will utilize a pragmatic, digitally-enabled, decentralized design to allow patients to consent and receive follow-up remotely without traveling to the study sites. SUMMARY: The REGAL trial will examine whether a consumer wearable device can serve as a long-term monitoring approach in older adults to detect AF and prevent cognitive function decline. If successful, the approach could have significant implications on how future clinical practice can leverage consumer devices for early diagnosis and disease prevention. CLINICALTRIALS: GOV: : NCT05923359.

Artificial intelligence-guided screening for atrial fibrillation using electrocardiogram during sinus rhythm: a prospective non-randomised interventional trial.

BACKGROUND: Previous atrial fibrillation screening trials have highlighted the need for more targeted approaches. We did a pragmatic study to evaluate the effectiveness of an artificial intelligence (AI) algorithm-guided targeted screening approach for identifying previously unrecognised atrial fibrillation. METHODS: For this non-randomised interventional trial, we prospectively recruited patients with stroke risk factors but with no known atrial fibrillation who had an electrocardiogram (ECG) done in routine practice. Participants wore a continuous ambulatory heart rhythm monitor for up to 30 days, with the data transmitted in near real time through a cellular connection. The AI algorithm was applied to the ECGs to divide patients into high-risk or low-risk groups. The primary outcome was newly diagnosed atrial fibrillation. In a secondary analysis, trial participants were propensity-score matched (1:1) to individuals from the eligible but unenrolled population who served as real-world controls. This study is registered with ClinicalTrials.gov, NCT04208971. FINDINGS: 1003 patients with a mean age of 74 years (SD 8·8) from 40 US states completed the study. Over a mean 22·3 days of continuous monitoring, atrial fibrillation was detected in six (1·6%) of 370 patients with low risk and 48 (7·6%) of 633 with high risk (odds ratio 4·98, 95% CI 2·11-11·75, p=0·0002). Compared with usual care, AI-guided screening was associated with increased detection of atrial fibrillation (high-risk group: 3·6% [95% CI 2·3-5·4] with usual care vs 10·6% [8·3-13·2] with AI-guided screening, p<0·0001; low-risk group: 0·9% vs 2·4%, p=0·12) over a median follow-up of 9·9 months (IQR 7·1-11·0). INTERPRETATION: An AI-guided targeted screening approach that leverages existing clinical data increased the yield for atrial fibrillation detection and could improve the effectiveness of atrial fibrillation screening. FUNDING: Mayo Clinic Robert D and Patricia E Kern Center for the Science of Health Care Delivery.

Screening for peripartum cardiomyopathies using artificial intelligence in Nigeria (SPEC-AI Nigeria): Clinical trial rationale and design.

BACKGROUND: Artificial intelligence (AI), and more specifically deep learning, models have demonstrated the potential to augment physician diagnostic capabilities and improve cardiovascular health if incorporated into routine clinical practice. However, many of these tools are yet to be evaluated prospectively in the setting of a rigorous clinical trial-a critical step prior to implementing broadly in routine clinical practice. OBJECTIVES: To describe the rationale and design of a proposed clinical trial aimed at evaluating an AI-enabled electrocardiogram (AI-ECG) for cardiomyopathy detection in an obstetric population in Nigeria. DESIGN: The protocol will enroll 1,000 pregnant and postpartum women who reside in Nigeria in a prospective randomized clinical trial. Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. Women aged 18 and older, seen for routine obstetric care at 6 sites (2 Northern and 4 Southern) in Nigeria will be included. Participants will be randomized to the study intervention or control arm in a 1:1 fashion. This study aims to enroll participants representative of the general obstetric population at each site. The primary outcome is a new diagnosis of cardiomyopathy, defined as left ventricular ejection fraction (LVEF) < 50% during pregnancy or within 12 months postpartum. Secondary outcomes will include the detection of impaired left ventricular function (at different LVEF cut-offs), and exploratory outcomes will include the effectiveness of AI-ECG tools for cardiomyopathy detection, new diagnosis of cardiovascular disease, and the development of composite adverse maternal cardiovascular outcomes. SUMMARY: This clinical trial focuses on the emerging field of cardio-obstetrics and will serve as foundational data for the use of AI-ECG tools in an obstetric population in Nigeria. This study will gather essential data regarding the utility of the AI-ECG for cardiomyopathy detection in a predominantly Black population of women and pave the way for clinical implementation of these models in routine practice. TRIAL REGISTRATION: Clinicaltrials.gov: NCT05438576.

Machine-learning-derived heart and brain age are independently associated with cognition.

BACKGROUND AND PURPOSE: A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. METHODS: Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40-85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. RESULTS: Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3-36) of the HDA effect on the tapping test score was mediated through BDA. DISCUSSION: Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Saliency maps provide insights into artificial intelligence-based electrocardiography models for detecting hypertrophic cardiomyopathy.

INTRODUCTION: A 12­lead electrocardiography (ECG)-based convolutional neural network (CNN) model can detect hypertrophic cardiomyopathy (HCM). However, since these models do not rely on discrete measurements as inputs, it is not apparent what drives their performance. We hypothesized that saliency maps could be used to visually identify ECG segments that contribute to a CNN's robust classification of HCM. METHODS: We derived a new one­lead (lead I) CNN model based on median beats using the same methodology and cohort used for the original 12­lead CNN model (3047 patients with HCM, and 63,926 sex- and age-matched non-HCM controls). One­lead, median-beat saliency maps were generated and visually evaluated in an independent cohort of 100 patients with a diagnosis of HCM and a high artificial intelligence (AI)-ECG-HCM probability score to determine which ECG segments contributed to the model's detection of HCM. RESULTS: The one­lead, median-beat CNN had an AUC of 0.90 (95% CI 0.89-0.92) for HCM detection, similar to the original 12­lead ECG model. In the independent HCM cohort (n = 100), saliency maps highlighted the ST-T segment in 92 ECGs, the atrial depolarization segment in 12 ECGs, and the QRS complex in 5 ECGs. CONCLUSIONS: Saliency maps of a one­lead, median-beat-based CNN model identified perturbations in ventricular repolarization as the main region of interest in detecting HCM.

Artificial Intelligence-Enabled Assessment of the Heart Rate Corrected QT Interval Using a Mobile Electrocardiogram Device.

BACKGROUND: Heart rate-corrected QT interval (QTc) prolongation, whether secondary to drugs, genetics including congenital long QT syndrome, and/or systemic diseases including SARS-CoV-2-mediated coronavirus disease 2019 (COVID-19), can predispose to ventricular arrhythmias and sudden cardiac death. Currently, QTc assessment and monitoring relies largely on 12-lead electrocardiography. As such, we sought to train and validate an artificial intelligence (AI)-enabled 12-lead ECG algorithm to determine the QTc, and then prospectively test this algorithm on tracings acquired from a mobile ECG (mECG) device in a population enriched for repolarization abnormalities. METHODS: Using >1.6 million 12-lead ECGs from 538 200 patients, a deep neural network (DNN) was derived (patients for training, n = 250 767; patients for testing, n = 107 920) and validated (n = 179 513 patients) to predict the QTc using cardiologist-overread QTc values as the "gold standard". The ability of this DNN to detect clinically-relevant QTc prolongation (eg, QTc ≥500 ms) was then tested prospectively on 686 patients with genetic heart disease (50% with long QT syndrome) with QTc values obtained from both a 12-lead ECG and a prototype mECG device equivalent to the commercially-available AliveCor KardiaMobile 6L. RESULTS: In the validation sample, strong agreement was observed between human over-read and DNN-predicted QTc values (-1.76±23.14 ms). Similarly, within the prospective, genetic heart disease-enriched dataset, the difference between DNN-predicted QTc values derived from mECG tracings and those annotated from 12-lead ECGs by a QT expert (-0.45±24.73 ms) and a commercial core ECG laboratory [10.52±25.64 ms] was nominal. When applied to mECG tracings, the DNN's ability to detect a QTc value ≥500 ms yielded an area under the curve, sensitivity, and specificity of 0.97, 80.0%, and 94.4%, respectively. CONCLUSIONS: Using smartphone-enabled electrodes, an AI DNN can predict accurately the QTc of a standard 12-lead ECG. QTc estimation from an AI-enabled mECG device may provide a cost-effective means of screening for both acquired and congenital long QT syndrome in a variety of clinical settings where standard 12-lead electrocardiography is not accessible or cost-effective.

Development of the AI-Cirrhosis-ECG Score: An Electrocardiogram-Based Deep Learning Model in Cirrhosis.

INTRODUCTION: Cirrhosis is associated with cardiac dysfunction and distinct electrocardiogram (ECG) abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. METHODS: A review of Mayo Clinic's electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years who underwent liver transplantation at the 3 Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease and then divided into training, validation, and test sets using a 70%-10%-20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. In addition, the association between the ACE score and the severity of patients' liver disease was assessed. RESULTS: The model's area under the curve in the test set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing model for end-stage liver disease-sodium score. Longitudinal trends in the ACE scores before and after liver transplantation mirrored the progression and resolution of liver disease. DISCUSSION: The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.

Migraine with aura associates with a higher artificial intelligence: ECG atrial fibrillation prediction model output compared to migraine without aura in both women and men.

OBJECTIVE: To compare the artificial intelligence-enabled electrocardiogram (AI-ECG) atrial fibrillation (AF) prediction model output in patients with migraine with aura (MwA) and migraine without aura (MwoA). BACKGROUND: MwA is associated with an approximately twofold risk of ischemic stroke. Longitudinal cohort studies showed that patients with MwA have a higher incidence of developing AF compared to those with MwoA. The Mayo Clinic Cardiology team developed an AI-ECG algorithm that calculates the probability of concurrent paroxysmal or impending AF in ECGs with normal sinus rhythm (NSR). METHODS: Adult patients with an MwA or MwoA diagnosis and at least one NSR ECG within the past 20 years at Mayo Clinic were identified. Patients with an ECG-confirmed diagnosis of AF were excluded. For each patient, the ECG with the highest AF prediction model output was used as the index ECG. Comparisons between MwA and MwoA were conducted in the overall group (including men and women of all ages), women only, and men only in each age range (18 to <35, 35 to <55, 55 to <75, ≥75 years), and adjusted for age, sex, and six common vascular comorbidities that increase risk for AF. RESULTS: The final analysis of our cross-sectional study included 40,002 patients (17,840 with MwA, 22,162 with MwoA). The mean (SD) age at the index ECG was 48.2 (16.0) years for MwA and 45.9 (15.0) years for MwoA (p < 0.001). The AF prediction model output was significantly higher in the MwA group compared to MwoA (mean [SD] 7.3% [15.0%] vs. 5.6% [12.4%], mean difference [95% CI] 1.7% [1.5%, 2.0%], p < 0.001). After adjusting for vascular comorbidities, the difference between MwA and MwoA remained significant in the overall group (least square means of difference [95% CI] 0.7% [0.4%, 0.9%], p < 0.001), 18 to <35 (0.4% [0.1%, 0.7%], p = 0.022), and 35 to <55 (0.5% [0.2%, 0.8%], p < 0.001), women of all ages (0.6% [0.3%, 0.8%], p < 0.001), men of all ages (1.0% [0.4%, 1.6%], p = 0.002), women 35 to <55 (0.6% [0.3%, 0.9%], p < 0.001), and men 18 to <35 (1.2% [0.3%, 2.1%], p = 0.008). CONCLUSIONS: Utilizing a novel AI-ECG algorithm on a large group of patients, we demonstrated that patients with MwA have a significantly higher AF prediction model output, implying a higher probability of concurrent paroxysmal or impending AF, compared to MwoA in both women and men. Our results suggest that MwA is an independent risk factor for AF, especially in patients <55 years old, and that AF-mediated cardioembolism may play a role in the migraine-stroke association for some patients.

Evaluating atrial fibrillation artificial intelligence for the ED: statistical and clinical implications.

OBJECTIVE: An artificial intelligence (AI) algorithm has been developed to detect the electrocardiographic signature of atrial fibrillation (AF) present on an electrocardiogram (ECG) obtained during normal sinus rhythm. We evaluated the ability of this algorithm to predict incident AF in an emergency department (ED) cohort of patients presenting with palpitations without concurrent AF. METHODS: This retrospective study included patients 18 years and older who presented with palpitations to one of 15 ED sites and had a 12­lead ECG performed. Patients with prior AF or newly diagnosed AF during the ED visit were excluded. Of the remaining patients, those with a follow up ECG or Holter monitor in the subsequent year were included. We evaluated the performance of the AI-ECG output to predict incident AF within one year of the index ECG by estimating an area under the receiver operating characteristics curve (AUC). Sensitivity, specificity, and positive and negative predictive values were determined at the optimum threshold (maximizing sensitivity and specificity), and thresholds by output decile for the sample. RESULTS: A total of 1403 patients were included. Forty-three (3.1%) patients were diagnosed with new AF during the following year. The AI-ECG algorithm predicted AF with an AUC of 0.74 (95% CI 0.68-0.80), and an optimum threshold with sensitivity 79.1% (95% Confidence Interval (CI) 66.9%-91.2%), and specificity 66.1% (95% CI 63.6%-68.6%). CONCLUSIONS: We found this AI-ECG AF algorithm to maintain statistical significance in predicting incident AF, with clinical utility for screening purposes limited in this ED population with a low incidence of AF.

Artificial Intelligence Applied to Cardiomyopathies: Is It Time for Clinical Application?

PURPOSE OF REVIEW: Artificial intelligence (AI) techniques have the potential to remarkably change the practice of cardiology in order to improve and optimize outcomes in heart failure and specifically cardiomyopathies, offering us novel tools to interpret data and make clinical decisions. The aim of this review is to describe the contemporary state of AI and digital health applied to cardiomyopathies as well as to define a potential pivotal role of its application by physicians in clinical practice. RECENT FINDINGS: Many studies have been undertaken in recent years on cardiomyopathy screening especially using AI-enhanced electrocardiography (ECG). Even with mild left ventricular (LV) dysfunction, AI-ECG screening for amyloidosis, hypertrophic cardiomyopathy, or dilated cardiomyopathy is now feasible. Introduction of AI-ECG in routine clinical care has resulted in higher detection of LV systolic dysfunction; however, clinical research on a broader scale with diverse populations is necessary and ongoing. In the area of cardiac-imaging, AI automatically assesses the thickness and characteristics of myocardium to differentiate cardiomyopathies, but research on its prognostic capability has yet to be conducted. AI is also being applied to cardiomyopathy genomics, especially to predict pathogenicity of variants and identify whether these variants are clinically actionable. While the implementation of AI in the diagnosis and treatment of cardiomyopathies is still in its infancy, an ever-growing clinical research strategy will ascertain the clinical utility of these AI tools to help improve diagnosis of and outcomes in cardiomyopathies. We also need to standardize the tools used to monitor the performance of AI-based systems which can then be used to expedite decision-making and rectify any hidden biases. Given its potential important role in clinical practice, healthcare providers need to familiarize themselves with the promise and limitations of this technology.

Application of artificial intelligence to the electrocardiogram.

Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.

Electrocardiogram screening for aortic valve stenosis using artificial intelligence.

AIMS: Early detection of aortic stenosis (AS) is becoming increasingly important with a better outcome after aortic valve replacement in asymptomatic severe AS patients and a poor outcome in moderate AS. We aimed to develop artificial intelligence-enabled electrocardiogram (AI-ECG) using a convolutional neural network to identify patients with moderate to severe AS. METHODS AND RESULTS: Between 1989 and 2019, 258 607 adults [mean age 63 ± 16.3 years; women 122 790 (48%)] with an echocardiography and an ECG performed within 180 days were identified from the Mayo Clinic database. Moderate to severe AS by echocardiography was present in 9723 (3.7%) patients. Artificial intelligence training was performed in 129 788 (50%), validation in 25 893 (10%), and testing in 102 926 (40%) randomly selected subjects. In the test group, the AI-ECG labelled 3833 (3.7%) patients as positive with the area under the curve (AUC) of 0.85. The sensitivity, specificity, and accuracy were 78%, 74%, and 74%, respectively. The sensitivity increased and the specificity decreased as age increased. Women had lower sensitivity but higher specificity compared with men at any age groups. The model performance increased when age and sex were added to the model (AUC 0.87), which further increased to 0.90 in patients without hypertension. Patients with false-positive AI-ECGs had twice the risk for developing moderate or severe AS in 15 years compared with true negative AI-ECGs (hazard ratio 2.18, 95% confidence interval 1.90-2.50). CONCLUSION: An AI-ECG can identify patients with moderate or severe AS and may serve as a powerful screening tool for AS in the community.

Batch enrollment for an artificial intelligence-guided intervention to lower neurologic events in patients with undiagnosed atrial fibrillation: rationale and design of a digital clinical trial.

BACKGROUND: Clinical trials are a fundamental tool to evaluate medical interventions but are time-consuming and resource-intensive. OBJECTIVES: To build infrastructure for digital trials to improve efficiency and generalizability and test it using a study to validate an artificial intelligence algorithm to detect atrial fibrillation (AF). DESIGN: We will prospectively enroll 1,000 patients who underwent an electrocardiogram for any clinical reason in routine practice, do not have a previous diagnosis of AF or atrial flutter and would be eligible for anticoagulation if AF is detected. Eligible patients will be identified using digital phenotyping algorithms, including natural language processing that runs on the electronic health records. Study invitations will be sent in batches via patient portal or letter, which will direct patients to a website to verify eligibility, learn about the study (including video-based informed consent), and consent electronically. The method aims to enroll participants representative of the general patient population, rather than a convenience sample of patients presenting to clinic. A device will be mailed to patients to continuously monitor for up to 30 days. The primary outcome is AF diagnosis and burden; secondary outcomes include patients' experience with the trial conduct methods and the monitoring device. The enrollment, intervention, and follow-up will be conducted remotely, ie, a patient-centered site-less trial. SUMMARY: This is among the first wave of trials to adopt digital technologies, artificial intelligence, and other pragmatic features to create efficiencies, which will pave the way for future trials in a broad range of disease and treatment areas. Clinicaltrials.gov: NCT04208971.

An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction.

BACKGROUND: Atrial fibrillation is frequently asymptomatic and thus underdetected but is associated with stroke, heart failure, and death. Existing screening methods require prolonged monitoring and are limited by cost and low yield. We aimed to develop a rapid, inexpensive, point-of-care means of identifying patients with atrial fibrillation using machine learning. METHODS: We developed an artificial intelligence (AI)-enabled electrocardiograph (ECG) using a convolutional neural network to detect the electrocardiographic signature of atrial fibrillation present during normal sinus rhythm using standard 10-second, 12-lead ECGs. We included all patients aged 18 years or older with at least one digital, normal sinus rhythm, standard 10-second, 12-lead ECG acquired in the supine position at the Mayo Clinic ECG laboratory between Dec 31, 1993, and July 21, 2017, with rhythm labels validated by trained personnel under cardiologist supervision. We classified patients with at least one ECG with a rhythm of atrial fibrillation or atrial flutter as positive for atrial fibrillation. We allocated ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. We calculated the area under the curve (AUC) of the receiver operatoring characteristic curve for the internal validation dataset to select a probability threshold, which we applied to the testing dataset. We evaluated model performance on the testing dataset by calculating the AUC and the accuracy, sensitivity, specificity, and F1 score with two-sided 95% CIs. FINDINGS: We included 180 922 patients with 649 931 normal sinus rhythm ECGs for analysis: 454 789 ECGs recorded from 126 526 patients in the training dataset, 64 340 ECGs from 18 116 patients in the internal validation dataset, and 130 802 ECGs from 36 280 patients in the testing dataset. 3051 (8·4%) patients in the testing dataset had verified atrial fibrillation before the normal sinus rhythm ECG tested by the model. A single AI-enabled ECG identified atrial fibrillation with an AUC of 0·87 (95% CI 0·86-0·88), sensitivity of 79·0% (77·5-80·4), specificity of 79·5% (79·0-79·9), F1 score of 39·2% (38·1-40·3), and overall accuracy of 79·4% (79·0-79·9). Including all ECGs acquired during the first month of each patient's window of interest (ie, the study start date or 31 days before the first recorded atrial fibrillation ECG) increased the AUC to 0·90 (0·90-0·91), sensitivity to 82·3% (80·9-83·6), specificity to 83·4% (83·0-83·8), F1 score to 45·4% (44·2-46·5), and overall accuracy to 83·3% (83·0-83·7). INTERPRETATION: An AI-enabled ECG acquired during normal sinus rhythm permits identification at point of care of individuals with atrial fibrillation. FUNDING: None.

ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial.

BACKGROUND: A deep learning algorithm to detect low ejection fraction (EF) using routine 12-lead electrocardiogram (ECG) has recently been developed and validated. The algorithm was incorporated into the electronic health record (EHR) to automatically screen for low EF, encouraging clinicians to obtain a confirmatory transthoracic echocardiogram (TTE) for previously undiagnosed patients, thereby facilitating early diagnosis and treatment. OBJECTIVES: To prospectively evaluate a novel artificial intelligence (AI) screening tool for detecting low EF in primary care practices. DESIGN: The EAGLE trial is a pragmatic two-arm cluster randomized trial (NCT04000087) that will randomize >100 clinical teams (i.e., clusters) to either intervention (access to the new AI screening tool) or control (usual care) at 48 primary care practices across Minnesota and Wisconsin. The trial is expected to involve approximately 400 clinicians and 20,000 patients. The primary endpoint is newly discovered EF ≤50%. Eligible patients will include adults who undergo ECG for any reason and have not been previously diagnosed with low EF. Data will be pulled from the EHR, and no contact will be made with patients. A positive deviance qualitative study and a post-implementation survey will be conducted among select clinicians to identify facilitators and barriers to using the new screening report. SUMMARY: This trial will examine the effectiveness of the AI-enabled ECG for detection of asymptomatic low EF in routine primary care practices and will be among the first to prospectively evaluate the value of AI in real-world practice. Its findings will inform future implementation strategies for the translation of other AI-enabled algorithms.

Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction.

OBJECTIVES: We sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12-lead electrocardiogram (ECG) in a large prospective cohort. BACKGROUND: Patients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging. METHODS: We applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new "positive screens." RESULTS: Among 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 "false-positives screens," 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT-pro-BNP after the initial "positive screen." CONCLUSIONS: A deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.

Safety and compatibility of smart device heart rhythm monitoring in patients with cardiovascular implantable electronic devices.

INTRODUCTION: Emerging medical technology has allowed for monitoring of heart rhythm abnormalities using smartphone compatible devices. The safety and utility of such devices have not been established in patients with cardiac implantable electronic devices (CIEDs). We sought to assess the safety and compatibility of the Food and Drug Administration-approved AliveCor Kardia device in patients with CIEDs. METHODS AND RESULTS: We prospectively recruited patients with CIED for a Kardia recording during their routine device interrogation. A recording was obtained in paced and nonpaced states. Adverse clinical events were noted at the time of recording. Electrograms (EGMs) from the cardiac device were obtained at the time of recording to assess for any electromagnetic interference (EMI) introduced by Kardia. Recordings were analyzed for quality and given a score of 3 (interpretable rhythm, no noise), 2 (interpretable rhythm, significant noise) or 1 (uninterpretable). A total of 251 patients were recruited (59% with a pacemaker and 41% with ICD). There were no adverse clinical events noted at the time of recording and no changes to CIED settings. Review of all EGMs revealed no EMI introduced by Kardia. Recordings were correctly interpreted in 90% of paced recordings (183 had a score of 3, 43 of 2, and 25 of 1) and 94.7% of nonpaced recordings (147 of 3, 15 of 2, and 9 of 1). CONCLUSION: The AliveCor Kardia device has an excellent safety profile when used in conjunction with most CIEDs. The quality of recordings was preserved in this population. The device, therefore, can be considered for heart rhythm monitoring in patients with CIEDs.