Artificial Intelligence-Enhanced Electrocardiography Identifies Patients With Normal Ejection Fraction at Risk of Worse Outcomes.

Background: An artificial intelligence (AI)-based electrocardiogram (ECG) model identifies patients with a higher likelihood of low ejection fraction (EF). Patients with an abnormal AI-ECG score but normal EF (false positives; FP) more often developed future low EF. Objective: The purpose of this study was to evaluate echocardiographic characteristics and all-cause mortality risk in FP patients. Methods: Patients with transthoracic echocardiography and ECG were classified retrospectively into FP, true negatives (TN) (EF ≥50%, normal AI-ECG), true positives (TP) (EF <50%, abnormal AI-ECG), or false negatives (FN) (EF <50%, normal AI-ECG). Echocardiographic abnormalities included systolic and diastolic left ventricular function, valve disease, estimated pulmonary pressures, and right heart parameters. Cox regression was used to assess factors associated with all-cause mortality. Results: Of 100,586 patients (median age 63 years; 45.5% females), 79% were TN, 7% FP, 5% FN, and 8% TP. FPs had more echocardiographic abnormalities than TN but less than FN or TP patients. An echocardiographic abnormality was present in 97% of FPs. Over median 2.7 years, FPs had increased mortality risk (age and sex-adjusted HR: 1.64 [95% CI: 1.55-1.73]) vs TN. Age and sex-adjusted mortality was higher in FP with abnormal echocardiography than FP with normal echocardiography and to TN regardless of echocardiography result; FP with normal echocardiography had comparable mortality risk to TN with abnormal echocardiography. Conclusions: FP patients were more likely than TNs to have echocardiographic abnormalities with 97% of exams showing an abnormality. FP patients had higher mortality rates, especially when their echocardiograms also had an abnormality; the concomitant use of AI ECG and echocardiography helps in stratifying risk in patients with normal LVEF.

Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial.

Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. This open-label, pragmatic clinical trial randomized pregnant and postpartum women to usual care or artificial intelligence (AI)-guided screening to assess its impact on the diagnosis left ventricular systolic dysfunction (LVSD) in the perinatal period. The study intervention included digital stethoscope recordings with point of-care AI predictions and a 12-lead electrocardiogram with asynchronous AI predictions for LVSD. The primary end point was identification of LVSD during the study period. In the intervention arm, the primary end point was defined as the number of identified participants with LVSD as determined by a positive AI screen, confirmed by echocardiography. In the control arm, this was the number of participants with clinical recognition and documentation of LVSD on echocardiography in keeping with current standard of care. Participants in the intervention arm had a confirmatory echocardiogram at baseline for AI model validation. A total of 1,232 (616 in each arm) participants were randomized and 1,195 participants (587 intervention arm and 608 control arm) completed the baseline visit at 6 hospitals in Nigeria between August 2022 and September 2023 with follow-up through May 2024. Using the AI-enabled digital stethoscope, the primary study end point was met with detection of 24 out of 587 (4.1%) versus 12 out of 608 (2.0%) patients with LVSD (intervention versus control odds ratio 2.12, 95% CI 1.05-4.27; P = 0.032). With the 12-lead AI-electrocardiogram model, the primary end point was detected in 20 out of 587 (3.4%) versus 12 out of 608 (2.0%) patients (odds ratio 1.75, 95% CI 0.85-3.62; P = 0.125). A similar direction of effect was observed in prespecified subgroup analysis. There were no serious adverse events related to study participation. In pregnant and postpartum women, AI-guided screening using a digital stethoscope improved the diagnosis of pregnancy-related cardiomyopathy. ClinicalTrials.gov registration: NCT05438576.

Performance of AI-Enabled Electrocardiogram in the Prediction of Metabolic Dysfunction-Associated Steatotic Liver Disease.

BACKGROUND AND AIMS: Accessible noninvasive screening tools for metabolic dysfunction-associated steatotic liver disease (MASLD) are needed. We aim to explore the performance of a deep learning-based artificial intelligence (AI) model in distinguishing the presence of MASLD using 12-lead electrocardiogram (ECG). METHODS: This is a retrospective study of adults diagnosed with MASLD in Olmsted County, Minnesota, between 1996 and 2019. Both cases and controls had ECGs performed within 6 years before and 1 year after study entry. An AI-based ECG model using a convolutional neural network was trained, validated, and tested in 70%, 10%, and 20% of the cohort, respectively. External validation was performed in an independent cohort from Mayo Clinic Enterprise. The primary outcome was the performance of ECG to identify MASLD, alone or when added to clinical parameters. RESULTS: A total of 3468 MASLD cases and 25,407 controls were identified. The AI-ECG model predicted the presence of MASLD with an area under the curve (AUC) of 0.69 (original cohort) and 0.62 (validation cohort). The performance was similar or superior to age- and sex-adjusted models using body mass index (AUC, 0.71), presence of diabetes, hypertension or hyperlipidemia (AUC, 0.68), or diabetes alone (AUC, 0.66). The model combining ECG, age, sex, body mass index, diabetes, and alanine aminotransferase had the highest AUC: 0.76 (original) and 0.72 (validation). CONCLUSIONS: This is a proof-of-concept study that an AI-based ECG model can detect MASLD with a comparable or superior performance as compared with the models using a single clinical parameter but not superior to the combination of clinical parameters. ECG can serve as another screening tool for MASLD in the nonhepatology space.

Artificial Intelligence Enabled Interpretation of ECG Images to Predict Hematopoietic Cell Transplantation Toxicity.

Artificial intelligence enabled interpretation of electrocardiogram waveform images (AI-ECG) can identify patterns predictive of future adverse cardiac events. We hypothesized such an approach, which is well described in general medical and surgical patients, would provide prognostic information with respect to the risk of cardiac complications and overall mortality in patients undergoing hematopoietic cell transplantation (HCT) for blood malignancy. We retrospectively subjected ECGs obtained pre-HCT to an externally trained, deep learning model designed to predict risk of atrial fibrillation (AF). Included were 1,377 patients (849 autologous HCT and 528 allogeneic HCT recipients). Median follow-up was 2.9 years. The three-year cumulative incidence of AF was 9% (95% CI: 7-12%) in autologous HCT patients and 13% (10-16%) in allogeneic HCT patients. In the entire cohort, pre-HCT AI-ECG estimate of AF risk correlated highly with development of clinical AF (Hazard Ratio (HR) 7.37, 3.53-15.4, p <0.001), inferior overall survival (HR: 2.4; 1.3-4.5, p = 0.004), and greater risk of non-relapse mortality (HR 3.36, 1.39-8.13, p = 0.007), without increased risk of relapse. Significant associations with mortality were only noted in allo HCT recipients, where the risk of non-relapse mortality was greater. Compared to calcineurin inhibitor-based graft versus host disease prophylaxis, the use of post-transplantation cyclophosphamide resulted in greater 90-day incidence of AF (13% versus 5%, p = 0.01), corresponding to temporal changes in AI-ECG AF prediction post HCT. In summary, AI-ECG can inform risk of post-transplant cardiac outcomes and survival in HCT patients and represents a novel strategy for personalized risk assessment after HCT.

Bridging ECG learning with emerging technologies: Advancing clinical excellence.

As ECG technology rapidly evolves to improve patient care, accurate ECG interpretation will continue to be foundational for maintaining high clinical standards. Recent studies have exposed significant educational gaps, with many healthcare professionals lacking sufficient training and proficiency. Furthermore, integrating new software and hardware ECG technologies poses challenges about potential knowledge and skill erosion. This underscores the need for clinicians who are adept at integrating clinical expertise with technological proficiency. It also highlights the need for innovative solutions to enhance ECG interpretation among healthcare professionals in this rapidly evolving environment. This work explores the importance of aligning ECG education with technological advancements and proposes how this synergy could advance patient care in the future.

Pediatric sex estimation using AI-enabled ECG analysis: influence of pubertal development.

AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. We aimed to test the ability of AI-enabled ECGs to predict sex in the pediatric population and study the influence of pubertal development. AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 90,133 unique pediatric patients (aged ≤18 years) recorded between 1987-2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0-7 years), peripubertal (8-14 years), and postpubertal (15-18 years) patients. The cohort was 46.7% male, with 21,678 prepubertal, 26,740 peripubertal, and 41,715 postpubertal children. The de novo pediatric model demonstrated 81% accuracy and an area under the curve (AUC) of 0.91. Model sensitivity was 0.79, specificity was 0.83, positive predicted value was 0.84, and the negative predicted value was 0.78, for the entire test cohort. The model's discriminatory ability was highest in postpubertal (AUC = 0.98), lower in the peripubertal age group (AUC = 0.91), and poor in the prepubertal age group (AUC = 0.67). There was no significant performance difference observed between the transfer learning and de novo models. AI-enabled interpretation of ECG can estimate sex in peripubertal and postpubertal children with high accuracy.

Hypertrophic cardiomyopathy detection with artificial intelligence electrocardiography in international cohorts: an external validation study.

Aims: Recently, deep learning artificial intelligence (AI) models have been trained to detect cardiovascular conditions, including hypertrophic cardiomyopathy (HCM), from the 12-lead electrocardiogram (ECG). In this external validation study, we sought to assess the performance of an AI-ECG algorithm for detecting HCM in diverse international cohorts. Methods and results: A convolutional neural network-based AI-ECG algorithm was developed previously in a single-centre North American HCM cohort (Mayo Clinic). This algorithm was applied to the raw 12-lead ECG data of patients with HCM and non-HCM controls from three external cohorts (Bern, Switzerland; Oxford, UK; and Seoul, South Korea). The algorithm's ability to distinguish HCM vs. non-HCM status from the ECG alone was examined. A total of 773 patients with HCM and 3867 non-HCM controls were included across three sites in the merged external validation cohort. The HCM study sample comprised 54.6% East Asian, 43.2% White, and 2.2% Black patients. Median AI-ECG probabilities of HCM were 85% for patients with HCM and 0.3% for controls (P < 0.001). Overall, the AI-ECG algorithm had an area under the receiver operating characteristic curve (AUC) of 0.922 [95% confidence interval (CI) 0.910-0.934], with diagnostic accuracy 86.9%, sensitivity 82.8%, and specificity 87.7% for HCM detection. In age- and sex-matched analysis (case-control ratio 1:2), the AUC was 0.921 (95% CI 0.909-0.934) with accuracy 88.5%, sensitivity 82.8%, and specificity 90.4%. Conclusion: The AI-ECG algorithm determined HCM status from the 12-lead ECG with high accuracy in diverse international cohorts, providing evidence for external validity. The value of this algorithm in improving HCM detection in clinical practice and screening settings requires prospective evaluation.

Direct Comparison of Methods to Differentiate Wide Complex Tachycardias: Novel Automated Algorithms Versus Manual ECG Interpretation Approaches.

BACKGROUND: Differentiating wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide tachycardia via 12-lead ECG interpretation is a crucial but difficult task. Automated algorithms show promise as alternatives to manual ECG interpretation, but direct comparison of their diagnostic performance has not been undertaken. METHODS: Two electrophysiologists applied 3 manual WCT differentiation approaches (ie, Brugada, Vereckei aVR, and VT score). Simultaneously, computerized data from paired WCT and baseline ECGs were processed by 5 automated WCT differentiation algorithms (WCT Formula, WCT Formula II, VT Prediction Model, Solo Model, and Paired Model). The diagnostic performance of automated algorithms was compared with manual ECG interpretation approaches. RESULTS: A total of 212 WCTs (111 VT and 101 supraventricular wide tachycardia) from 104 patients were analyzed. WCT Formula demonstrated superior accuracy (85.8%) and specificity (87.1%) compared with Brugada (75.2% and 57.4%, respectively) and Vereckei aVR (65.3% and 36.4%, respectively). WCT Formula II achieved higher accuracy (89.6%) and specificity (85.1%) against Brugada and Vereckei aVR. Performance metrics of the WCT Formula (accuracy 85.8%, sensitivity 84.7%, and specificity 87.1%) and WCT Formula II (accuracy 89.8%, sensitivity 89.6%, and specificity 85.1%) were similar to the VT score (accuracy 84.4%, sensitivity 93.8%, and specificity 74.2%). Paired Model was superior to Brugada in accuracy (89.6% versus 75.2%), specificity (97.0% versus 57.4%), and F1 score (0.89 versus 0.80). Paired Model surpassed Vereckei aVR in accuracy (89.6% versus 65.3%), specificity (97.0% versus 75.2%), and F1 score (0.89 versus 0.74). Paired Model demonstrated similar accuracy (89.6% versus 84.4%), inferior sensitivity (79.3% versus 93.8%), but superior specificity (97.0% versus 74.2%) to the VT score. Solo Model and VT Prediction Model accuracy (82.5% and 77.4%, respectively) was superior to the Vereckei aVR (65.3%) but similar to Brugada (75.2%) and the VT score (84.4%). CONCLUSIONS: Automated WCT differentiation algorithms demonstrated favorable diagnostic performance compared with traditional manual ECG interpretation approaches.

Vigorous Exercise in Patients With Congenital Long QT Syndrome: Results of the Prospective, Observational, Multinational LIVE-LQTS Study.

BACKGROUND: Whether vigorous exercise increases risk of ventricular arrhythmias for individuals diagnosed and treated for congenital long QT syndrome (LQTS) remains unknown. METHODS: The National Institutes of Health-funded LIVE-LQTS study (Lifestyle and Exercise in the Long QT Syndrome) prospectively enrolled individuals 8 to 60 years of age with phenotypic and/or genotypic LQTS from 37 sites in 5 countries from May 2015 to February 2019. Participants (or parents) answered physical activity and clinical events surveys every 6 months for 3 years with follow-up completed in February 2022. Vigorous exercise was defined as ≥6 metabolic equivalents for >60 hours per year. A blinded Clinical Events Committee adjudicated the composite end point of sudden death, sudden cardiac arrest, ventricular arrhythmia treated by an implantable cardioverter defibrillator, and likely arrhythmic syncope. A National Death Index search ascertained vital status for those with incomplete follow-up. A noninferiority hypothesis (boundary of 1.5) between vigorous exercisers and others was tested with multivariable Cox regression analysis. RESULTS: Among the 1413 participants (13% <18 years of age, 35% 18-25 years of age, 67% female, 25% with implantable cardioverter defibrillators, 90% genotype positive, 49% with LQT1, 91% were treated with beta-blockers, left cardiac sympathetic denervation, and/or implantable cardioverter defibrillator), 52% participated in vigorous exercise (55% of these competitively). Thirty-seven individuals experienced the composite end point (including one sudden cardiac arrest and one sudden death in the nonvigorous group, one sudden cardiac arrest in the vigorous group) with overall event rates at 3 years of 2.6% in the vigorous and 2.7% in the nonvigorous exercise groups. The unadjusted hazard ratio for experience of events for the vigorous group compared with the nonvigorous group was 0.97 (90% CI, 0.57-1.67), with an adjusted hazard ratio of 1.17 (90% CI, 0.67-2.04). The upper 95% one-sided confidence level extended beyond the 1.5 boundary. Neither vigorous or nonvigorous exercise was found to be superior in any group or subgroup. CONCLUSIONS: Among individuals diagnosed with phenotypic and/or genotypic LQTS who were risk assessed and treated in experienced centers, LQTS-associated cardiac event rates were low and similar between those exercising vigorously and those not exercising vigorously. Consistent with the low event rate, CIs are wide, and noninferiority was not demonstrated. These data further inform shared decision-making discussions between patient and physician about exercise and competitive sports participation. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT02549664.

Artificial intelligence-based screening for cardiomyopathy in an obstetric population: A pilot study.

Background: Cardiomyopathy is a leading cause of pregnancy-related mortality and the number one cause of death in the late postpartum period. Delay in diagnosis is associated with severe adverse outcomes. Objective: To evaluate the performance of an artificial intelligence-enhanced electrocardiogram (AI-ECG) and AI-enabled digital stethoscope to detect left ventricular systolic dysfunction in an obstetric population. Methods: We conducted a single-arm prospective study of pregnant and postpartum women enrolled at 3 sites between October 28, 2021, and October 27, 2022. Study participants completed a standard 12-lead ECG, digital stethoscope ECG and phonocardiogram recordings, and a transthoracic echocardiogram within 24 hours. Diagnostic performance was evaluated using the area under the curve (AUC). Results: One hundred women were included in the final analysis. The median age was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, and 21% as Hispanic. Five percent and 6% had left ventricular ejection fraction (LVEF) <45% and <50%, respectively. The AI-ECG model had near-perfect classification performance (AUC: 1.0, 100% sensitivity; 99%-100% specificity) for detection of cardiomyopathy at both LVEF categories. The AI-enabled digital stethoscope had an AUC of 0.98 (95% CI: 0.95, 1.00) and 0.97 (95% CI: 0.93, 1.00), for detection of LVEF <45% and <50%, respectively, with 100% sensitivity and 90% specificity. Conclusion: We demonstrate an AI-ECG and AI-enabled digital stethoscope were effective for detecting cardiac dysfunction in an obstetric population. Larger studies, including an evaluation of the impact of screening on clinical outcomes, are essential next steps.

Rationale, design, and participant characteristics of the FAITH! Heart Health+ study: An exploration of the influence of the social determinants of health, stress, and structural racism on African American cardiovascular health.

BACKGROUND: African Americans (AAs) face cardiovascular health (CVH) disparities linked to systemic racism. The 2020 police killing of Mr. George Floyd in Minneapolis, Minnesota, alongside the COVID-19 pandemic, exacerbated adverse psychosocial factors affecting CVH outcomes among AAs. This manuscript describes the study protocol and participant characteristics in an ancillary study exploring the relationship between biopsychosocial factors and CVH among AAs. METHODS: Using a community-based participatory approach, a mixed-methods ancillary study of 58 AA participants from an overarching randomized control trial (RCT) was conducted. Baseline RCT health assessments (November 2020) provided sociodemographic, medical, and clinical data. Subsequent health assessments (February-December 2022) measured sleep quality, psychosocial factors (e.g., high-effort coping), biomarkers (e.g., cortisol), and cardiovascular diagnostics (e.g., cardio-ankle vascular index). CVH was assessed using the American Heart Association Life's Simple 7 (LS7) (range 0 to 14, poor to ideal) and Life's Essential 8 (LE8) scores (range 0 to 100, low to high). Correlations between these scores will be examined. Focus group discussions via videoconferencing (March to April 2022) assessed psychosocial and structural barriers, along with the impact of COVID-19 and George Floyd's killing on daily life. RESULTS: Participants were predominantly female (67%), with a mean age of 54.6 [11.9] years, high cardiometabolic risk (93% had overweight/obesity and 70% hypertension), and moderate LE8 scores (mean 57.4, SD 11.5). CONCLUSION: This study will enhance understanding of the associations between biopsychosocial factors and CVH among AAs in Minnesota. Findings may inform risk estimation, patient care, and healthcare policies to address CVD disparities in marginalized populations.

Screening for Unrecognized HFpEF in Atrial Fibrillation and for Unrecognized Atrial Fibrillation in HFpEF.

Because of the bidirectional relationship between atrial fibrillation (AF) and heart failure with preserved ejection fraction (HFpEF), individuals with either condition require consideration of screening for the other. In this review, we summarize current evidence and rationale for screening for occult HFpEF in adults with clinical AF; and occult AF in patients with clinically recognized HFpEF. Assessment of pretest probability for occult HFpEF in symptomatic AF patients may help guide additional testing such as exercise right heart catheterization to diagnose HFpEF and guide HFpEF-specific therapies. In patients with HFpEF, AF screening will identify cases of occult AF where anticoagulation may decrease stroke risk, and correlation of previously unknown AF episodes with paroxysmal symptoms may prompt consideration for rhythm control. Therefore, screening may help clinicians understand the etiology of the often-overlapping symptoms, and it may help guide treatments to slow progression of both conditions and their complications.

Ten-Year Trend of Oral Anticoagulation Use in Postoperative and Nonpostoperative Atrial Fibrillation in Routine Clinical Practice.

BACKGROUND: The study aimed to describe the patterns and trends of initiation, discontinuation, and adherence of oral anticoagulation (OAC) in patients with new-onset postoperative atrial fibrillation (POAF), and compare with patients newly diagnosed with non-POAF. METHODS AND RESULTS: This retrospective cohort study identified patients newly diagnosed with atrial fibrillation or flutter between 2012 and 2021 using administrative claims data from OptumLabs Data Warehouse. The POAF cohort included 118 366 patients newly diagnosed with atrial fibrillation or flutter within 30 days after surgery. The non-POAF cohort included the remaining 315 832 patients who were newly diagnosed with atrial fibrillation or flutter but not within 30 days after a surgery. OAC initiation increased from 28.9% to 44.0% from 2012 to 2021 in POAF, and 37.8% to 59.9% in non-POAF; 12-month medication adherence increased from 47.0% to 61.8% in POAF, and 59.7% to 70.4% in non-POAF. The median time to OAC discontinuation was 177 days for POAF, and 242 days for non-POAF. Patients who saw a cardiologist within 90 days of the first atrial fibrillation or flutter diagnosis, regardless of POAF or non-POAF, were more likely to initiate OAC (odds ratio, 2.92 [95% CI, 2.87-2.98]; P <0.0001), adhere to OAC (odds ratio, 1.08 [95% CI, 1.04-1.13]; P <0.0001), and less likely to discontinue (odds ratio, 0.83 [95% CI, 0.82-0.85]; P <0.0001) than patients who saw a surgeon or other specialties. CONCLUSIONS: The use of and adherence to OAC were higher in non-POAF patients than in POAF patients, but they increased over time in both groups. Patients managed by cardiologists were more likely to use and adhere to OAC, regardless of POAF or non-POAF.

Artificial Intelligence Electrocardiography to Predict Atrial Fibrillation in Patients With Chronic Lymphocytic Leukemia.

Background: The use of an artificial intelligence electrocardiography (AI-ECG) algorithm has demonstrated its reliability in predicting the risk of atrial fibrillation (AF) within the general population. Objectives: This study aimed to determine the effectiveness of the AI-ECG score in identifying patients with chronic lymphocytic leukemia (CLL) who are at high risk of developing AF. Methods: We estimated the probability of AF based on AI-ECG among patients with CLL extracted from the Mayo Clinic CLL database. Additionally, we computed the Mayo Clinic CLL AF risk score and determined its ability to predict AF. Results: Among 754 newly diagnosed patients with CLL, 71.4% were male (median age = 69 years). The median baseline AI-ECG score was 0.02 (range = 0-0.93), with a value ≥0.1 indicating high risk. Over a median follow-up of 5.8 years, the estimated 10-year cumulative risk of AF was 26.1%. Patients with an AI-ECG score of ≥0.1 had a significantly higher risk of AF (HR: 3.9; 95% CI: 2.6-5.7; P < 0.001). This heightened risk remained significant (HR: 2.5; 95% CI: 1.6-3.9; P < 0.001) even after adjusting for the Mayo CLL AF risk score, heart failure, chronic kidney disease, and CLL therapy. In a second cohort of CLL patients treated with a Bruton tyrosine kinase inhibitor (n = 220), a pretreatment AI-ECG score ≥0.1 showed a nonsignificant increase in the risk of AF (HR: 1.7; 95% CI: 0.8-3.6; P = 0.19). Conclusions: An AI-ECG algorithm, in conjunction with the Mayo CLL AF risk score, can predict the risk of AF in patients with newly diagnosed CLL. Additional studies are needed to determine the role of AI-ECG in predicting AF risk in CLL patients treated with a Bruton tyrosine kinase inhibitor.

Unlocking the potential of artificial intelligence in electrocardiogram biometrics: age-related changes, anomaly detection, and data authenticity in mobile health platforms.

Aims: Mobile devices such as smartphones and watches can now record single-lead electrocardiograms (ECGs), making wearables a potential screening tool for cardiac and wellness monitoring outside of healthcare settings. Because friends and family often share their smart phones and devices, confirmation that a sample is from a given patient is important before it is added to the electronic health record. Methods and results: We sought to determine whether the application of Siamese neural network would permit the diagnostic ECG sample to serve as both a medical test and biometric identifier. When using similarity scores to discriminate whether a pair of ECGs came from the same patient or different patients, inputs of single-lead and 12-lead medians produced an area under the curve of 0.94 and 0.97, respectively. Conclusion: The similar performance of the single-lead and 12-lead configurations underscores the potential use of mobile devices to monitor cardiac health.