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.

An electrocardiogram (ECG)-based artificial intelligence (AI) algorithm has shown good performance in detecting hypertrophic cardiomyopathy (HCM). However, its application in routine clinical practice may be challenging owing to the low disease prevalence and potentially high false-positive rates.Identify clinical characteristics associated with true- and false-positive HCM AI-ECG results to improve its clinical application.We reviewed the records of the 200 patients with highest HCM AI-ECG scores in January 2021 at our institution. Logistic regression was used to create a clinical variable-based "Candidacy for HCM Detection (HCM-DETECT)" score, differentiating true-positive from false-positive AI-ECG results. We validated the HCM-DETECT score in an independent cohort of 200 patients with the highest AI-ECG scores from January 2022.In the 2021 cohort (median age 71 [interquartile range 58-80] years, 48% female), the rates of true-positive, false-positive, and indeterminate AI-ECG results for HCM detection were 36%, 48%, and 16%, respectively. In the 2022 cohort, the rates were 26%, 47%, and 27%, respectively. The HCM-DETECT score included age, coronary artery disease, prior pacemaker, and prior cardiac valve surgery, and had an area under the receiver operating characteristic curve of 0.81 (95% confidence interval 0.73-0.87) for differentiating true- vs false-positive AI results. When the 2022 cohort was limited to HCM detection candidates identified with the HCM-DETECT score, the false-positive AI-ECG rate was reduced from 47% to 13.5%.Application of a clinical score (HCM-DETECT) in tandem with an AI-ECG model improved HCM detection yield, reducing the false-positive rate of AI-ECG more than 3-fold.

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.

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.

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.

Artificial intelligence (AI)-based approaches can now use electrocardiograms (ECGs) to provide expert-level performance in detecting heart abnormalities and diagnosing disease. Additionally, patient age predicted from ECGs by AI models has shown great potential as a biomarker for cardiovascular age, where recent work has found its deviation from chronological age (“delta age”) to be associated with mortality and co-morbidities. However, despite being crucial for understanding underlying individual risk, the genetic underpinning of delta age is unknown. In this work we performed a genome-wide association study using UK Biobank data (n=34,432) and identified eight loci associated with delta age ($$p\le 5 \times 10^{-8}$$ p ≤ 5 × 10 - 8 ), including genes linked to cardiovascular disease (CVD) (e.g. SCN5A) and (heart) muscle development (e.g. TTN). Our results indicate that the genetic basis of cardiovascular ageing is predominantly determined by genes directly involved with the cardiovascular system rather than those connected to more general mechanisms of ageing. Our insights inform the epidemiology of CVD, with implications for preventative and precision medicine.

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.

Artificial intelligence (AI)-based approaches can now use electrocardiograms (ECGs) to provide expert-level performance in detecting heart abnormalities and diagnosing disease. Additionally, patient age predicted from ECGs by AI models has shown great potential as a biomarker for cardiovascular age, where recent work has found its deviation from chronological age ("delta age") to be associated with mortality and co-morbidities. However, despite being crucial for understanding underlying individual risk, the genetic underpinning of delta age is unknown. In this work we performed a genome-wide association study using UK Biobank data (n=34,432) and identified eight loci associated with delta age ([Formula: see text]), including genes linked to cardiovascular disease (CVD) (e.g. SCN5A) and (heart) muscle development (e.g. TTN). Our results indicate that the genetic basis of cardiovascular ageing is predominantly determined by genes directly involved with the cardiovascular system rather than those connected to more general mechanisms of ageing. Our insights inform the epidemiology of CVD, with implications for preventative and precision medicine.

To characterize the utility of an existing electrocardiogram (ECG)-artificial intelligence (AI) algorithm of left ventricular dysfunction (LVD) in immune-mediated necrotizing myopathy (IMNM).A retrospective cohort observational study was conducted within our tertiary-care neuromuscular clinic for patients with IMNM meeting European Neuromuscular Centre diagnostic criteria (January 1, 2000, to December 31, 2020). A validated AI algorithm using 12-lead standard ECGs to detect LVD was applied. The output was presented as a percent probability of LVD. Electrocardiograms before and while on immunotherapy were reviewed. The LVD-predicted probability scores were compared with echocardiograms, immunotherapy treatment response, and mortality.The ECG-AI algorithm had acceptable accuracy in LVD prediction in 74% (68 of 89) of patients with IMNM with available echocardiograms (discrimination threshold, 0.74; 95% CI, 0.6-0.87). This translates into a sensitivity of 80.0% and specificity of 62.8% to detect LVD. Best cutoff probability prediction was 7 times more likely to have LVD (odds ratio, 6.75; 95% CI, 2.11-21.51;In IMNM, an AI-ECG algorithm assists detection of LVD, enhancing the decision to advance to echocardiogram testing, while also informing on mortality risk, which is important in the decision of immunotherapy escalation and monitoring.

With the emergence of artificial intelligence (AI)-based health interventions, systemic racism remains a concern as these advancements are frequently developed without race-specific data analysis or validation. To evaluate the potential utility of an AI-based cardiovascular diseases (CVD) screening tool in an under-resourced African-American cohort, we reviewed the AI-enhanced electrocardiogram (ECG) data of participants enrolled in a community-based clinical trial as a proof-of-concept ancillary study for community-based screening.Enrollees completed cardiovascular testing including standard 12-lead ECG and a limited echocardiogram (TTE). All ECGs were analyzed using previously published institution-based AI algorithms. AI-ECG predictions were generated for age, sex, and decreased left ventricular ejection fraction (LVEF). Diagnostic accuracy of the AI-ECG for decreased LVEF and sex was quantified using area under the receiver operating characteristic curve (AUC). Correlation between actual age and AI-ECG predicted age was assessed using Pearson correlation coefficients.Fifty-four participants completed both an ECG and TTE (mean age 55 years [range 31-87 years]; 66.7% female). All participants were in sinus rhythm, and the median LVEF of the cohort was 60-65%. The AI-ECG for decreased LVEF demonstrated excellent performance with an AUC of 0.892 (95% confidence interval [CI] 0.708-1); sensitivity=50% (95% CI 9.5-90.5%; n=1/2) and specificity=96% (95% CI 86.8-98.9%; n=49/51). The AI-ECG for participant sex demonstrated similar performance with AUC of 0.944 (95% CI 0.891-0.998); sensitivity=100% (95% CI 82.4-100.0%; n=18/18) and specificity=77.8% (95% CI 61.9-88.3%; n=28/36). The AI-ECG predicted mean age was 55 years (range 26.9-72.6 years) with a strong correlation to actual age (R=0.769; p0.001).Our analyses of previously developed AI-ECG algorithms for prediction of age, sex, and decreased LVEF demonstrated reliable performance in this community-based, African-American cohort. This novel, community-centric delivery of AI could provide valuable screening resources and appropriate referrals for early detection of highly-morbid CVD for under-resourced patient populations.

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 Many digital health technologies capable of atrial fibrillation (AF) detection are directly available to patients. However, adaptation into clinical practice by heart rhythm healthcare practitioners (HCPs) is unclear. Objective To examine HCP perspectives on use of commercial technologies for AF detection and management. Methods We created an electronic survey for HCPs assessing practice demographics and perspectives on digital devices for AF detection and management. The survey was distributed electronically to all members of 3 heart rhythm professional societies. Results We received 1601 responses out of 73,563 e-mails sent, with 43.6% from cardiac electrophysiologists, 12.8% from fellows, and 11.6% from advanced practice practitioners. Most respondents (62.3%) reported having recommended patient use of a digital device for AF detection. Those who did not had concerns about their accuracy (29.6%), clinical utility of results (22.8%), and integration into electronic health records (19.8%). Results from a 30-second single-lead electrocardiogram were sufficient for 42.7% of HCPs to recommend oral anticoagulation for patients at high risk for stroke. Respondents wanted more data comparing the accuracy of digital devices to conventional devices for AF monitoring (64.9%). A quarter (27.3%) of HCPs had no reservations recommending digital devices for AF detection, and most (53.4%) wanted guidelines from their professional societies providing guidance on their optimal use. Conclusion Many HCPs have already integrated digital devices into their clinical practice. However, HCPs reported facing challenges when using digital technologies for AF detection, and professional society recommendations on their use are needed.

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.

Objective To develop an artificial intelligence (AI)–enabled electrocardiogram (ECG) algorithm capable of comprehensive, human-like ECG interpretation and compare its diagnostic performance against conventional ECG interpretation methods. Methods We developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, no changes needed), (2) acceptable (ie, minor edits needed), or (3) unacceptable (ie, major edits needed). Results Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as ideal from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as acceptable from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. Conclusion An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.

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.This retrospective study included patients 18 years and older who presented with palpitations to one of 15 ED sites and had a 12‑lead 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.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%).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.

Background: Left atrial (LA) myopathy is common in patients with heart failure and preserved ejection fraction and leads to the development of atrial fibrillation (AF). We investigated whether the likelihood of LA remodeling, LA dysfunction, altered hemodynamics, and risk for incident AF could be identified from a single 12-lead ECG using a novel artificial intelligence (AI)-enabled ECG analysis. Methods: Patients with heart failure and preserved ejection fraction (n=613) underwent AI-enabled ECG analysis, echocardiography, and cardiac catheterization. Individuals were grouped by AI-enabled ECG probability of contemporaneous AF, taken as an indicator of underlying LA myopathy. Results: Structural heart disease was more severe in patients with higher AI-probability of AF, with more left ventricular hypertrophy, larger LA volumes, and lower LA reservoir and booster strain. Cardiac filling pressures and pulmonary artery pressures were higher in patients with higher AI-probability, while cardiac output reserve was more impaired during exercise. Among patients with sinus rhythm and no prior AF, each 10% increase in AI-probability was associated with a 31% greater risk of developing new-onset AF (hazard ratio, 1.31 [95% CI, 1.20–1.42]; P P Conclusions: A novel AI-enabled score derived from a single 12-lead ECG identifies the presence of underlying LA myopathy in patients with heart failure and preserved ejection fraction as evidenced by structural, functional, and hemodynamic abnormalities, as well as long-term risk for incident AF. Further research is required to determine the role of the AI-enabled ECG in the evaluation and care of patients with heart failure and preserved ejection fraction.

Background Cardiovascular disease (CVD) has been identified as a major threat to maternal health in the US and UK with cardiomyopathy being one of the most common acquired CVD in the pregnant and postpartum period. Diagnosing cardiomyopathy in pregnancy is challenging due to an overlap of cardiovascular symptoms with normal pregnancy symptoms. Purpose The purpose of this study was to evaluate the effectiveness of an ECG based deep learning model in identifying cardiomyopathy among pregnant and postpartum women. Methods We utilized an ECG based deep learning model to detect cardiomyopathy in a cohort of pregnant or postpartum women seen at multiple hospital sites. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, and specificity. We compared the diagnostic probabilities of the deep learning model with natriuretic peptides and a multivariable model consisting of demographic and clinical parameters. Results 1,807 women were included. 7%, 10% and 13% had LVEF ≤35%, Conclusions A deep learning model effectively identifies cardiomyopathy in pregnant or postpartum women, outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): This study was made possible using resources supported by the Mayo Clinic Women's Health Research Center and the Mayo Clinic Building Interdisciplinary Research Careers in Women's Health (BIRCWH) Program funded by the National Institutes of Health (NIH), grant number K12 HD065987. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Background An artificial intelligence (AI) algorithm detecting age from 12-lead ECG has been suggested to signal “physiological age” of the individual. Importantly, increased physiological age gauged by an increased difference between ECG-age and chronological age has been associated with higher risk of cardiac events in non-transplant population. Purpose We sought to investigate the validity of the AI-derived ECG-age algorithm in patients who underwent heart transplantation and its relationship to major adverse cardiovascular events (MACE). Methods A total of 489 consecutive patients who had undergone heart transplantation in our institution between 1994 and 2018 were studied. AI-ECG age was calculated by a previously-trained artificial intelligence (AI) algorithm using a 12-lead ECG per patient. ECGs used in the training process of the algorithm were excluded. The average of the ECG-ages within one year before and one year after heart transplantation was used to represent pre- and post-transplant ECG-ages. MACE was defined as any incidence of revascularization, re-transplantation, and death. Results Pre-transplant ECG-age (mean 63±10 years) correlated significantly with recipient chronological age (mean 50±13 years, r=0.57, p Conclusion Post-transplant ECG-age correlates more faithfully with the donor's than the recipient's chronological age, suggesting that ECG-age more closely reflects cardiac age than the patient age. Furthermore, ECG-age derived cardiac aging after transplantation is associated with higher risk of MACE. Funding Acknowledgement Type of funding sources: None.