Search

Aims Current non-invasive screening methods for cardiac allograft rejection have shown limited discrimination and are yet to be broadly integrated into heart transplant care. Given electrocardiogram (ECG) changes have been reported with severe cardiac allograft rejection, this study aimed to develop a deep-learning model, a form of artificial intelligence, to detect allograft rejection using the 12-lead ECG (AI-ECG). Methods and results Heart transplant recipients were identified across three Mayo Clinic sites between 1998 and 2021. Twelve-lead digital ECG data and endomyocardial biopsy results were extracted from medical records. Allograft rejection was defined as moderate or severe acute cellular rejection (ACR) based on International Society for Heart and Lung Transplantation guidelines. The extracted data (7590 unique ECG-biopsy pairs, belonging to 1427 patients) was partitioned into training (80%), validation (10%), and test sets (10%) such that each patient was included in only one partition. Model performance metrics were based on the test set (n = 140 patients; 758 ECG-biopsy pairs). The AI-ECG detected ACR with an area under the receiver operating curve (AUC) of 0.84 [95% confidence interval (CI): 0.78–0.90] and 95% (19/20; 95% CI: 75–100%) sensitivity. A prospective proof-of-concept screening study (n = 56; 97 ECG-biopsy pairs) showed the AI-ECG detected ACR with AUC = 0.78 (95% CI: 0.61–0.96) and 100% (2/2; 95% CI: 16–100%) sensitivity. Conclusion An AI-ECG model is effective for detection of moderate-to-severe ACR in heart transplant recipients. Our findings could improve transplant care by providing a rapid, non-invasive, and potentially remote screening option for cardiac allograft function.

Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. We digitally enrolled 2,454 unique patients (mean age 53 ± 15 years, 56% female) from 46 US states and 11 countries, who sent 125,610 ECGs to the data platform between August 2021 and February 2022; 421 participants had at least one watch-classified sinus rhythm ECG within 30 d of an echocardiogram, of whom 16 (3.8%) had an EF ≤ 40%. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823–0.946) and 0.881 (0.815–0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.

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.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, NCT04208971.1003 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, p0·0001; 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).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.Mayo Clinic Robert D and Patricia E Kern Center for the Science of Health Care Delivery.

AimsAn artificial intelligence algorithm detecting age from 12-lead electrocardiogram (ECG) has been suggested to reflect ‘physiological age’. An increased physiological age has been associated with a higher risk of cardiac mortality in the non-transplant population. We aimed to investigate the utility of this algorithm in patients who underwent heart transplantation (HTx).Methods and resultsA total of 540 patients were studied. The average ECG ages within 1 year before and after HTx were used to represent pre- and post-HTx ECG ages. Major adverse cardiovascular event (MACE) was defined as any coronary revascularization, heart failure hospitalization, re-transplantation, and mortality. Recipient pre-transplant ECG age (mean 63 ± 11 years) correlated significantly with recipient chronological age (mean 49 ± 14 years, R = 0.63, P < 0.0001), while post-transplant ECG age (mean 54 ± 10 years) correlated with both the donor (mean 32 ± 13 years, R = 0.45, P < 0.0001) and the recipient ages (R = 0.38, P < 0.0001). During a median follow-up of 8.8 years, 307 patients experienced MACE. Patients with an increase in ECG age post-transplant showed an increased risk of MACE [hazard ratio (HR): 1.58, 95% confidence interval (CI): (1.24, 2.01), P = 0.0002], even after adjusting for potential confounders [HR: 1.58, 95% CI: (1.19, 2.10), P = 0.002].ConclusionElectrocardiogram age-derived cardiac ageing after transplantation is associated with a higher risk of MACE. This study suggests that physiological age change of the heart might be an important determinant of MACE risk post-HTx.

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.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.

Aims Electrocardiogram (ECG)-enabled stethoscope (ECG-Scope) acquires a single-lead ECGs during cardiac auscultation and may facilitate real-time screening for pathologies not routinely identified by cardiac auscultation alone. We previously demonstrated an artificial intelligence (AI) algorithm can identify left ventricular dysfunction (LVSD) [defined as ejection fraction (EF) ≤ 40%] with an area under the curve (AUC) of 0.91 using a 12-lead ECG. Methods and results One hundred patients referred for clinically indicated echocardiography were prospectively recruited. ECG-Scope recordings with the patient supine and sitting were obtained in multiple electrode locations at the time of the echocardiogram. The AI algorithm for the detection of LVSD was retrained using single leads from ECG-12 and validated against ECG-Scope to determine accuracy for low EF detection (≤35%, Conclusion An AI algorithm applied to an ECG-enabled stethoscope recording in standard auscultation positions reliably detected the presence of a low EF in this prospective study of patients referred for echocardiography. The ability to screen patients with a possible low EF during routine physical examination may facilitate rapid detection of LVSD.

Aims Some artificial intelligence models applied in medical practice require ongoing retraining, introduce unintended racial bias, or have variable performance among different subgroups of patients. We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm’s long-term efficacy and potential bias in the absence of retraining. Methods and results Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. Time series analysis of the model validated its temporal stability. Areas under the curve were similar for all racial and ethnic groups (0.90–0.92) with minimal performance difference between sexes. Patients with a ‘normal sinus rhythm’ electrocardiogram (n = 37 047) exhibited an AUC of 0.91. All other electrocardiogram features had areas under the curve between 0.79 and 0.91, with the lowest performance occurring in the left bundle branch block group (0.79). Conclusion The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.

Aims Artificial intelligence (AI) enabled electrocardiography (ECG) can detect latent atrial fibrillation (AF) in patients with sinus rhythm (SR). However, the change of AI-ECG probability before and after the first AF episode is not well characterized. We sought to characterize the temporal trend of AI-ECG AF probability around the first episode of AF. Methods and results We retrospectively studied adults who had at least one ECG in SR prior to an ECG that documented AF. An AI network calculated the AF probability from ECGs during SR (positive defined >8.7%, based on optimal sensitivity and specificity). The AI-ECG probability was reported prior to and after the first episode of AF and stratified by age and CHA2DS2-VASc score. Mixed effect models were used to assess the rate of change between time points. A total of 59 212 patients with 544 330 ECGs prior to AF and 413 486 ECGs after AF were included. The mean time between the first positive AI-ECG and first AF was 5.4 ± 5.7 years. The mean AI-ECG probability was 19.8% 2–5 years prior to AF, 23.6% 1–2 years prior to AF, 34.0% 0–3 months prior to AF, 40.9% 0–3 months after AF, 35.2% 1–2 years after AF, and 42.2% 2–5 years after AF (P 50 years CHA2DS2-VASc score ≥4. Conclusion The AI-ECG probability progressively increases with time prior to the first AF episode, transiently decreases 1–2 years following AF and continues to increase thereafter.

Aims Our goal was to evaluate a previously validated artificial intelligence–augmented electrocardiography (AI-ECG) screening tool for left ventricular systolic dysfunction (LVSD) in patients undergoing high-sensitivity-cardiac troponin T (hs-cTnT). Methods and results Retrospective application of AI-ECG for LVSD in emergency department (ED) patients undergoing hs-cTnT. AI-ECG scores (0–1) for probability of LVSD (left ventricular ejection fraction ≤ 35%) were obtained. An AI-ECG score ≥0.256 indicates a positive screen. The primary endpoint was a composite of post-discharge major adverse cardiovascular events (MACEs) at two years follow-up. Among 1977 patients, 248 (13%) had a positive AI-ECG. When compared with patients with a negative AI-ECG, those with a positive AI-ECG had a higher risk for MACE [48 vs. 21%, P < 0.0001, adjusted hazard ratio (HR) 1.39, 95% confidence interval (CI) 1.11–1.75]. This was largely because of a higher rate of deaths (32 vs. 14%, P < 0.0001; adjusted HR 1.26, 95% 0.95–1.66) and heart failure hospitalizations (26 vs. 6.1%, P < 0.001; adjusted HR 1.75, 95% CI 1.25–2.45). Together, hs-cTnT and AI-ECG resulted in the following MACE rates and adjusted HRs: hs-cTnT < 99th percentile and negative AI-ECG: 116/1176 (11%; reference), hs-cTnT < 99th percentile and positive AI-ECG: 28/107 (26%; adjusted HR 1.54, 95% CI 1.01–2.36), hs-cTnT > 99th percentile and negative AI-ECG: 233/553 (42%; adjusted HR 2.12, 95% CI 1.66, 2.70), and hs-cTnT > 99th percentile and positive AI-ECG: 91/141 (65%; adjusted HR 2.83, 95% CI 2.06, 3.87). Conclusion Among ED patients evaluated with hs-cTnT, a positive AI-ECG for LVSD identifies patients at high risk for MACE. The conjoint use of hs-cTnT and AI-ECG facilitates risk stratification.

To assess whether an electrocardiography-based artificial intelligence (AI) algorithm developed to detect severe ventricular dysfunction (left ventricular ejection fraction [LVEF] of 35% or below) independently predicts long-term mortality after cardiac surgery among patients without severe ventricular dysfunction (LVEF35%).Patients who underwent valve or coronary bypass surgery at Mayo Clinic (1993-2019) and had documented LVEF above 35% on baseline electrocardiography were included. We compared patients with an abnormal vs a normal AI-enhanced electrocardiogram (AI-ECG) screen for LVEF of 35% or below on preoperative electrocardiography. The primary end point was all-cause mortality.A total of 20,627 patients were included, of whom 17,125 (83.0%) had a normal AI-ECG screen and 3502 (17.0%) had an abnormal AI-ECG screen. Patients with an abnormal AI-ECG screen were older and had more comorbidities. Probability of survival at 5 and 10 years was 86.2% and 68.2% in patients with a normal AI-ECG screen vs 71.4% and 45.1% in those with an abnormal screen (log-rank, P.01). In the multivariate Cox survival analysis, the abnormal AI-ECG screen was independently associated with a higher all-cause mortality overall (hazard ratio [HR], 1.31; 95% CI, 1.24 to 1.37) and in subgroups of isolated valve surgery (HR, 1.30; 95% CI, 1.18 to 1.42), isolated coronary artery bypass grafting (HR, 1.29; 95% CI, 1.20 to 1.39), and combined coronary artery bypass grafting and valve surgery (HR, 1.19; 95% CI, 1.08 to 1.32). In a subgroup analysis, the association between abnormal AI-ECG screen and mortality was consistent in patients with LVEF of 35% to 55% and among those with LVEF above 55%.A novel electrocardiography-based AI algorithm that predicts severe ventricular dysfunction can predict long-term mortality among patients with LVEF above 35% undergoing valve and/or coronary bypass surgery.

Objective To develop an artificial intelligence (AI)–based tool to detect cardiac amyloidosis (CA) from a standard 12-lead electrocardiogram (ECG). Methods We collected 12-lead ECG data from 2541 patients with light chain or transthyretin CA seen at Mayo Clinic between 2000 and 2019. Cases were nearest neighbor matched for age and sex, with 2454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with an internal validation set (n=999; 20%) and a randomly selected holdout testing set (n=999; 20%). We performed experiments using single-lead and 6-lead ECG subsets. Results The area under the receiver operating characteristic curve (AUC) was 0.91 (CI, 0.90 to 0.93), with a positive predictive value for detecting either type of CA of 0.86. By use of a cutoff probability of 0.485 determined by the Youden index, 426 (84%) of the holdout patients with CA were detected by the model. Of the patients with CA and prediagnosis electrocardiographic studies, the AI model successfully predicted the presence of CA more than 6 months before the clinical diagnosis in 59%. The best single-lead model was V5 with an AUC of 0.86 and a precision of 0.78, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.90 and a precision of 0.85. Conclusion An AI-driven ECG model effectively detects CA and may promote early diagnosis of this life-threatening disease.

Aims The current gold standard comprehensive assessment of coronary microvascular dysfunction (CMD) is through a limited-access invasive catheterization lab procedure. We aimed to develop a point-of-care tool to assist clinical guidance in patients presenting with chest pain and/or an abnormal cardiac functional stress test and with non-obstructive coronary artery disease (NOCAD). Methods and results This study included 1893 NOCAD patients ( Conclusion An artificial intelligence-enabled algorithm may be able to assist clinical guidance by ruling out CMD in patients presenting with chest pain and/or an abnormal functional stress test. This algorithm needs to be prospectively validated in different cohorts.

There is no established screening approach for hypertrophic cardiomyopathy (HCM). We recently developed an artificial intelligence (AI) model for the detection of HCM based on the 12‑lead electrocardiogram (AI-ECG) in adults. Here, we aimed to validate this approach of ECG-based HCM detection in pediatric patients (age ≤ 18 years).We identified a cohort of 300 children and adolescents with HCM (mean age 12.5 ± 4.6 years, male 68%) who had an ECG and echocardiogram at our institution. Patients were age- and sex-matched to 18,439 non-HCM controls. Diagnostic performance of the AI-ECG model for the detection of HCM was estimated using the previously identified optimal diagnostic threshold of 11% (the probability output derived by the model above which an ECG is considered to belong to an HCM patient).Mean AI-ECG probabilities of HCM were 92% and 5% in the case and control groups, respectively. The area under the receiver operating characteristic curve (AUC) of the AI-ECG model for HCM detection was 0.98 (95% CI 0.98-0.99) with corresponding sensitivity 92% and specificity 95%. The positive and negative predictive values were 22% and 99%, respectively. The model performed similarly in males and females and in genotype-positive and genotype-negative HCM patients. Performance tended to be superior with increasing age. In the age subgroup5 years, the test's AUC was 0.93. In comparison, the AUC was 0.99 in the age subgroup 15-18 years.A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12‑lead ECG.

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., Graphical Abstract Graphical AbstractThe application of artificial intelligence to the standard electrocardiogram enables it to diagnose conditions not previously identifiable by an electrocardiogram, or to do so with a greater performance than previously possible. This includes identification of the current rhythm, identification of episodic atrial fibrillation from an ECG acquired during sinus rhythm, the presence of ventricular dysfunction (low ejection fraction), the presence of valvular heart disease, channelopathies (even when electrocardiographically ‘concealed’), and the presence of hypertrophic cardiomyopathy.

Undiagnosed dilated cardiomyopathy (DC) can be asymptomatic or present as sudden cardiac death, therefore pre-emptively identifying and treating patients may be beneficial. Screening for DC with echocardiography is expensive and labor intensive and standard electrocardiography (ECG) is insensitive and non-specific. The performance and applicability of artificial intelligence-enabled electrocardiography (AI-ECG) for detection of DC is unknown. Diagnostic performance of an AI algorithm in determining reduced left ventricular ejection fraction (LVEF) was evaluated in a cohort that comprised of DC and normal LVEF control patients. DC patients and controls with 12-lead ECGs and a reference LVEF measured by echocardiography performed within 30 and 180 days of the ECG respectively were enrolled. The model was tested for its sensitivity, specificity, negative predictive (NPV) and positive predictive values (PPV) based on the prevalence of DC at 1% and 5%. The cohort consisted of 421 DC cases (60% males, 57±15 years, LVEF 28±11%) and 16,025 controls (49% males, age 69 ±16 years, LVEF 62±5%). For detection of LVEF≤45%, the area under the curve (AUC) was 0.955 with a sensitivity of 98.8% and specificity 44.8%. The NPV and PPV were 100% and 1.8% at a DC prevalence of 1% and 99.9% and 8.6% at a prevalence of 5%, respectively. In conclusion AI-ECG demonstrated high sensitivity and negative predictive value for detection of DC and could be used as a simple and cost-effective screening tool with implications for screening first degree relatives of DC patients.

Aims We sought to investigate whether artificial intelligence (AI) and specifically deep neural networks (NNs) for electrocardiogram (ECG) signal analysis can be explained using human-selected features. We also sought to quantify such explainability and test if the AI model learns features that are similar to a human expert. Methods and results We used a set of 100 000 ECGs that were annotated by human explainable features. We applied both linear and non-linear models to predict published ECG AI models output for the detection of patients’ age and sex. We further used canonical correlation analysis to quantify the amount of shared information between the NN features and human-selected features. We reconstructed single human-selected ECG features from the unexplained NN features using a simple linear model. We noticed a strong correlation between the simple models and the AI output (R2 of 0.49–0.57 for the linear models and R2 of 0.69–0.70 for the non-linear models). We found that the correlation of the human explainable features with either 13 of the strongest age AI features or 15 of the strongest sex AI features was above 0.85 (for comparison, the first 14 principal components explain 90% of the human feature variance). We linearly reconstructed single human-selected ECG features from the AI features with R2 up to 0.86. Conclusion This work shows that NNs for ECG signals extract features in a similar manner to human experts and that they also generate additional novel features that help achieve superior performance.

We have conducted a pragmatic clinical trial aimed to assess whether an electrocardiogram (ECG)-based, artificial intelligence (AI)-powered clinical decision support tool enables early diagnosis of low ejection fraction (EF), a condition that is underdiagnosed but treatable. In this trial ( NCT04000087 ), 120 primary care teams from 45 clinics or hospitals were cluster-randomized to either the intervention arm (access to AI results; 181 clinicians) or the control arm (usual care; 177 clinicians). ECGs were obtained as part of routine care from a total of 22,641 adults (N = 11,573 intervention; N = 11,068 control) without prior heart failure. The primary outcome was a new diagnosis of low EF (≤50%) within 90 days of the ECG. The trial met the prespecified primary endpoint, demonstrating that the intervention increased the diagnosis of low EF in the overall cohort (1.6% in the control arm versus 2.1% in the intervention arm, odds ratio (OR) 1.32 (1.01–1.61), P = 0.007) and among those who were identified as having a high likelihood of low EF (that is, positive AI-ECG, 6% of the overall cohort) (14.5% in the control arm versus 19.5% in the intervention arm, OR 1.43 (1.08–1.91), P = 0.01). In the overall cohort, echocardiogram utilization was similar between the two arms (18.2% control versus 19.2% intervention, P = 0.17); for patients with positive AI-ECGs, more echocardiograms were obtained in the intervention compared to the control arm (38.1% control versus 49.6% intervention, P

Background We have demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG) [artificial intelligence (AI) ECG age]. However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. Methods and results We previously developed a convolutional neural network to predict chronological age from ECGs. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. Of 25 144 subjects tested (54% females, 95% Caucasian) followed for 12.4 ± 5.3 years, the mean chronological age was 53.7 ± 11.6 years and ECG-derived age was 54.6 ± 11 years (R2 = 0.79, P < 0.0001). The mean Age-Gap was small at 0.88 ± 7.4 years. Compared to those whose ECG-derived age was within 1 standard deviation (SD) of their chronological age, patients with Age-Gap ≥1 SD had higher all-cause and cardiovascular disease (CVD) mortality. Conversely, subjects whose Age-Gap was ≤1 SD had lower all-cause and CVD mortality. Results were unchanged after adjusting for CVD risk factors and other survival influencing factors. Conclusion The difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological ageing.

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.

Background Automated computerized electrocardiogram (ECG) interpretation algorithms are designed to enhance physician ECG interpretation, minimize medical error, and expedite clinical workflow. However, the performance of current computer algorithms is notoriously inconsistent. We aimed to develop and validate an artificial intelligence–enabled ECG (AI-ECG) algorithm capable of comprehensive 12-lead ECG interpretation with accuracy comparable to practicing cardiologists. Methods We developed an AI-ECG algorithm using a convolutional neural network as a multilabel classifier capable of assessing 66 discrete, structured diagnostic ECG codes using the cardiologist's final annotation as the gold-standard interpretation. We included 2,499,522 ECGs from 720,978 patients ≥18 years of age with a standard 12-lead ECG obtained at the Mayo Clinic ECG laboratory between 1993 and 2017. The total sample was randomly divided into training (n = 1,749,654), validation (n = 249,951), and testing (n = 499,917) datasets with a similar distribution of codes. We compared the AI-ECG algorithm's performance to the cardiologist's interpretation in the testing dataset using receiver operating characteristic (ROC) and precision recall (PR) curves. Results The model performed well for various rhythm, conduction, ischemia, waveform morphology, and secondary diagnoses codes with an area under the ROC curve of ≥0.98 for 62 of the 66 codes. PR metrics were used to assess model performance accounting for category imbalance and demonstrated a sensitivity ≥95% for all codes. Conclusions An AI-ECG algorithm demonstrates high diagnostic performance in comparison to reference cardiologist interpretation of a standard 12-lead ECG. The use of AI-ECG reading tools may permit scalability as ECG acquisition becomes more ubiquitous.

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.

This collaborative statement from the Digital Health Committee of the Heart Rhythm Society provides everyday clinical scenarios in which wearables may be utilized by patients for cardiovascular health and arrhythmia management. We describe herein the spectrum of wearables that are commercially available for patients, and their benefits, shortcomings and areas for technological improvement. Although wearables for rhythm diagnosis and management have not been examined in large randomized clinical trials, undoubtedly the usage of wearables has quickly escalated in clinical practice. This document is the first of a planned series in which we will update information on wearables as they are revised and released to consumers.