Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied Read more

Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied to a single-lead ECG, recorded during ECG-enabled stethoscope examination, to validate a potential point-of-care screening tool for LVEF of 40% or lower. We conducted an observational, prospective, multicentre study of a convolutional neural network (known as AI-ECG) that was previously validated for the detection of reduced LVEF using 12-lead ECG as input. We used AI-ECG retrained to interpret single-lead ECG input alone. Patients (aged ≥18 years) attending for transthoracic echocardiogram in London (UK) were recruited. All participants had 15 s of supine, single-lead ECG recorded at the four standard anatomical positions for cardiac auscultation, plus one handheld position, using an ECG-enabled stethoscope. Transthoracic echocardiogram-derived percentage LVEF was used as ground truth. The primary outcome was performance of AI-ECG at classifying reduced LVEF (LVEF ≤40%), measured using metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with two-sided 95% CIs. The primary outcome was reported for each position individually and with an optimal combination of AI-ECG outputs (interval range 0–1) from two positions using a rule-based approach and several classification models. Between Feb 6 and May 27, 2021, we recruited 1050 patients (mean age 62 years [SD 17·4], 535 [51%] male, 432 [41%] non-White). 945 (90%) had an ejection fraction of at least 40%, and 105 (10%) had an ejection fraction of 40% or lower. Across all positions, ECGs were most frequently of adequate quality for AI-ECG interpretation at the pulmonary position (979 [93·3%] of 1050). Quality was lowest for the aortic position (846 [80·6%]). AI-ECG performed best at the pulmonary valve position (p=0·02), with an AUROC of 0·85 (95% CI 0·81–0·89), sensitivity of 84·8% (76·2–91·3), and specificity of 69·5% (66·4–72·6). Diagnostic odds ratios did not differ by age, sex, or non-White ethnicity. Taking the optimal combination of two positions (pulmonary and handheld positions), the rule-based approach resulted in an AUROC of 0·85 (0·81–0·89), sensitivity of 82·7% (72·7–90·2), and specificity of 79·9% (77·0–82·6). Using AI-ECG outputs from these two positions, a weighted logistic regression with l2 regularisation resulted in an AUROC of 0·91 (0·88–0·95), sensitivity of 91·9% (78·1–98·3), and specificity of 80·2% (75·5–84·3). A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG-enabled stethoscope can detect LVEF of 40% or lower. These findings highlight the potential for inexpensive, non-invasive, workflow-adapted, point-of-care screening, for earlier diagnosis and prognostically beneficial treatment. Less

The objective of this study is 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 Cardiologists determined that on average Read more

The objective of this study is 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 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. An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation. Less

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 Read more

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. Less

We used decision analytic modeling to perform a cost-effectiveness analysis of the use of AI-ECG to screen for asymptomatic left ventricular dysfunction (ALVD) once at age 65 compared with no screening. This screening consisted of an initial screening decision tree and subsequent construction of a Read more

We used decision analytic modeling to perform a cost-effectiveness analysis of the use of AI-ECG to screen for asymptomatic left ventricular dysfunction (ALVD) once at age 65 compared with no screening. This screening consisted of an initial screening decision tree and subsequent construction of a Markov model. One-way sensitivity analysis on various disease and cost parameters to evaluate cost-effectiveness at both $50,000 per quality-adjusted life year (QALY) and $100,000 per QALY willingness-to-pay threshold. We found that for universal screening at age 65, the novel AI-ECG algorithm would cost $43,351 per QALY gained, test performance, disease characteristics, and testing cost parameters significantly affect cost-effectiveness, and screening at ages 55 and 75 would cost $48,649 and $52,072 per QALY gained, respectively. Overall, under most of the clinical scenarios modeled, coupled with its robust test performance in both testing and validation cohorts, screening with the novel AI-ECG algorithm appears to be cost-effective at a willingness-to-pay threshold of $50,000. Universal screening for ALVD with the novel AI-ECG appears to be cost-effective under most clinical scenarios with a cost of <$50,000 per QALY. Cost-effectiveness is particularly sensitive to both the probability of disease progression and the cost of screening and downstream testing. To improve cost-effectiveness modeling, further study of the natural progression and treatment of ALVD and external validation of AI-ECG should be undertaken. Less

The objective of this study is to build infrastructure for digital trials to improve efficiency and generalizability and test it using a study to validate an artificial intelligence algorithm to detect atrial fibrillation (AF). We will prospectively enroll 1,000 patients who underwent an Read more

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

Coronary artery calcium (CAC) scoring is recommended in adults with unclear cardiovascular (CV) risk to inform preventative strategies and has major limitations. We developed a deep learning (DL) algorithm to predict CAC from 12-lead electrocardiograms (ECG-AI). Historical cohort of 43,210 Read more

Coronary artery calcium (CAC) scoring is recommended in adults with unclear cardiovascular (CV) risk to inform preventative strategies and has major limitations. We developed a deep learning (DL) algorithm to predict CAC from 12-lead electrocardiograms (ECG-AI). Historical cohort of 43,210 consecutive patients that from 1997-2020 underwent clinically indicated CAC and ECG within 1 year. Age, sex and major modifiable CV risk factors were collected during medical visits. We excluded those on statins, paced rhythm, history of myocardial infarction or missing data. We trained a convolutional neural network based on ECG-AI output +/- CV risk factors to predict a high CAC score (≥ 300) on a random sample of 60% of the dataset, validated in 20%. We evaluated model performance with thresholds that yielded 90% sensitivity, in the remaining 20%. Mean ± SD age 55 ± 9.8, 31% women, 1,857 (20%) had CAC ≥ 300. Algorithm's AUC of the ROC, specificity, and accuracy was 77%, 38%, 44%, for ECG-AI only; and 83%, 56%, 60% for ECG-AI + age and sex; and 83%, 57%, 61% for ECG-AI, age, sex + CV risk factors. The ECG-AI + age and sex algorithm displayed equivalent performance when compared to the one including CV risk factors (p>0.05). Subgroup performance was constant, including those with no CV risk factors. The DL-enabled ECG can help predict a high CAC score, even without information on CV risk. This algorithm could improve selection of subjects with higher likelihood of CAC. Less

Graves' disease (GD) is known to be associated with atrial fibrillation (AF). Artificial intelligence (AI)-enabled ECGs using a convolutional neural network can identify the signature of silent AF. Whether the existing AI model is able to identify patients at highest risk of GD-related AF is Read more

Graves' disease (GD) is known to be associated with atrial fibrillation (AF). Artificial intelligence (AI)-enabled ECGs using a convolutional neural network can identify the signature of silent AF. Whether the existing AI model is able to identify patients at highest risk of GD-related AF is unknown. Patients with GD (2009-2019) at our institution were included. GD-associated AF was defined as AF diagnosed ≤30 days before or any time after GD. Probability of AF was obtained from the AI platform on ECGs in sinus rhythm done within 2 months before and up to 2 years after GD; when multiple ECGs were present, the earliest was considered. 430 patients with GD were included; mean age 50±17, 78% female. AF was diagnosed in 43 (10%) patients with a median (IQR) of 11 (0-863) days after GD. ECGs used were obtained 27 (4-690) days before AF. Univariate risk factors included older age [HR 1.07 (1.04-1.09) p <.001], male gender [HR 1.9 (1.01-3.6) p =.047], hypertension (HR 4.4 (2.2-8.8), p<.001), hyperlipidemia [HR 2.8 (1.5-5.1), p = .001], history of coronary artery disease [HR 5.0 (2.4-10.5), p <.001], chronic kidney disease [HR 2.9 (1.4-6.3), p =.006], and probability of AF >5% [HR 5.9 (3.2-10.9). p<.001]. At multivariate analysis, risk factors for AF were AI ECG probability of AF>5% [HR 4.2 (2.1-8.1), p<.001], older age [HR 1.05 (1.03-1.07) per year, p=<.001] and overt hyperthyroidism (free T4>1.7) [HR 3.4 (1.04-11.1) p = .04]. Model AUC was 0.84 (compared to 0.79 without ECG-derived AF probability) and chi square was 61 (compared to 43 without ECG-derived AF probability, p <.001). A clinical risk model based on AI-ECG, age and free T4 was strongly associated with developing GD-associated AF at follow-up. The AI-enabled ECG is available within the electronic medical record and could be easily incorporated in clinical-decision tools. Prospective validation of the model is currently underway. Less

Cardiac amyloidosis (CA) is a life-threatening disease with poor outcomes often related to delayed diagnosis. We developed an artificial-intelligence (AI) based screening tool that identifies CA from the 12 lead ECG as well as single and six lead acquisitions. We collected 12-lead ECG data for Read more

Cardiac amyloidosis (CA) is a life-threatening disease with poor outcomes often related to delayed diagnosis. We developed an artificial-intelligence (AI) based screening tool that identifies CA from the 12 lead ECG as well as single and six lead acquisitions. We collected 12-lead ECG data for 2,541 patients with light chain (AL) or transthyretin (ATTR) CA seen at Mayo Clinic from 2000-2019. These cases were propensity score-matched on age and sex with 2,454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with a 999 (20%) threshold-tuning set and a 999 (20%) holdout test set. We performed experiments using single lead and six lead ECG subsets. The area under the receiver operating characteristic curve (AUC) was 0.92 (CI = 0.90-0.94) with a precision (positive predictive value) for detecting either AL or ATTR-CA of 0.87. Using a cut-off probability of 0.5, 424 (83%) of the hold-out patients with CA were detected by the model. Of the CA patients with pre-diagnosis ECG studies, in 47% the AI model successfully predicted the presence of CA >six months before the clinical diagnosis (Fig.1). The best single lead model was V5 with an AUC of 0.83 and a precision of 0.84, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.88 and a precision of 0.89. An AI-driven ECG screening tool can effectively detect CA and may promote early detection of this life-threatening disease. Less

Hypertrophic cardiomyopathy (HCM) is a cause of morbidity and sudden cardiac death in children and adolescents. There is currently no established screening approach for HCM. We recently developed an artificial intelligence (AI) convolutional neural network (CNN) for the detection of HCM based on Read more

Hypertrophic cardiomyopathy (HCM) is a cause of morbidity and sudden cardiac death in children and adolescents. There is currently no established screening approach for HCM. We recently developed an artificial intelligence (AI) convolutional neural network (CNN) for the detection of HCM based on the 12-lead electrocardiogram (ECG) in an adult population. We aimed to validate this approach of ECG-based HCM detection in pediatric patients. We included 318 HCM patients (mean age 12±4.8 years, male 68%) and 22,996 age- and sex-matched non-HCM controls. AI-ECG probability for HCM was >11% in 91% of cases and 3% of controls. The AUC of the AI-ECG model for HCM detection was 0.98 (95% CI 0.97-0.99) with corresponding sensitivity 97% and specificity 91%. The model performed similarly in subgroups defined by gender and HCM genotype status. Model performance was best in the oldest subgroup (15-18 years) in both males and females. A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12-lead ECG. Less

The objective of this study was to validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population. LVSD, even when asymptomatic, confers increased morbidity and mortality. We recently derived AI-ECG to Read more

The objective of this study was to validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population. LVSD, even when asymptomatic, confers increased morbidity and mortality. We recently derived AI-ECG to detect LVSD using ECGs based on a large sample of patients treated at the Mayo Clinic. We performed an external validation study with subjects from the Know Your Heart Study, a cross-sectional study of adults aged 35-69 years residing in two cities in Russia, who had undergone both ECG and transthoracic echocardiography. LVSD was defined as left ventricular ejection fraction ≤ 35%. We assessed the performance of the AI-ECG to identify LVSD in this distinct patient population. Among 4277 subjects in this external population-based validation study, 0.6% had LVSD (compared to 7.8% of the original clinical derivation study). The overall performance of the AI-ECG to detect LVSD was robust with an area under the receiver operating curve of 0.82. When using the LVSD probability cut-off of 0.256 from the original derivation study, the sensitivity, specificity, and accuracy in this population were 26.9%, 97.4%, 97.0%, respectively. Other probability cut-offs were analysed for different sensitivity values. The AI-ECG detected LVSD with robust test performance in a population that was very different from that used to develop the algorithm. Population-specific cut-offs may be necessary for clinical implementation. Differences in population characteristics, ECG and echocardiographic data quality may affect test performance. Less

Atrial fibrillation (AF) is an established risk factor for ischemic stroke, but it can be paroxysmal and may go undiagnosed. An artificial intelligence (AI)-enabled ECG acquired during normal sinus rhythm was recently shown to detect silent AF. The objective of this study was to determine if AI-ECG Read more

Atrial fibrillation (AF) is an established risk factor for ischemic stroke, but it can be paroxysmal and may go undiagnosed. An artificial intelligence (AI)-enabled ECG acquired during normal sinus rhythm was recently shown to detect silent AF. The objective of this study was to determine if AI-ECG AF score is associated with presence of cerebral infarcts. This study included 1,373 individuals. Average age was 69.6 years and 53% of participants were male. There were 136 (10%) individuals with ECG-confirmed AF; 1237 (90%) participants had no AF history. Of participants with AF, 23% (n=31) were on anticoagulation, 47% (n=64) were on antiplatelet and 18% (n=24) were on dual therapy. Only 1.3% (n=16) of patients without AF were on anticoagulation and 47% (n=578) were on antiplatelet therapy. Ischemic infarcts were detected in 214 (15.6%) patients. As a continuous measure AI-ECG was associated with infarcts but not after adjusting for age and sex (p=0.46). AI-ECG AF score > 0.5 was associated with infarcts (p < 0.001); even after adjusting for age and sex (p= 0.03). History of AF was also associated with infarcts after adjusting for age and sex (p = 0.018). AI-ECG AF score and history of AF were associated with presence of cerebral infarcts after adjusting for age and sex. This tool could be useful in select patients with cryptogenic stroke but further investigation would be required. Less

One of the most critical and challenging skills is the distinction of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia. Prompt and accurate differentiation of wide complex tachycardias naturally influences short- and long-term management decisions Read more

One of the most critical and challenging skills is the distinction of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia. Prompt and accurate differentiation of wide complex tachycardias naturally influences short- and long-term management decisions and may directly affect patient outcomes. Currently, there are many useful electrocardiographic criteria and algorithms designed to distinguish ventricular tachycardia and supraventricular wide complex tachycardia accurately; however, no single approach guarantees diagnostic certainty. In this review, we offer an in-depth analysis of available methods to differentiate wide complex tachycardias by retrospectively examining its rich literature base - one that spans several decades. Less

An artificial intelligence (AI) algorithm applied to electrocardiography during sinus rhythm has recently been shown to detect concurrent episodic atrial fibrillation (AF). We sought to characterize the value of AI–enabled electrocardiography (AI-ECG) as a predictor of future AF and assess its Read more

An artificial intelligence (AI) algorithm applied to electrocardiography during sinus rhythm has recently been shown to detect concurrent episodic atrial fibrillation (AF). We sought to characterize the value of AI–enabled electrocardiography (AI-ECG) as a predictor of future AF and assess its performance compared with the CHARGE-AF score (Cohorts for Aging and Research in Genomic Epidemiology–AF) in a population-based sample. We calculated the probability of AF using AI-ECG, among participants in the population-based Mayo Clinic Study of Aging who had no history of AF at the time of the baseline study visit. Cox proportional hazards models were fit to assess the independent prognostic value and interaction between AI-ECG AF model output and CHARGE-AF score. C statistics were calculated for AI-ECG AF model output, CHARGE-AF score, and combined AI-ECG and CHARGE-AF score. A total of 1936 participants with median age 75.8 (interquartile range, 70.4–81.8) years and median CHARGE-AF score 14.0 (IQR, 13.2–14.7) were included in the analysis. Participants with AI-ECG AF model output of >0.5 at the baseline visit had cumulative incidence of AF 21.5% at 2 years and 52.2% at 10 years. When included in the same model, both AI-ECG AF model output (hazard ratio, 1.76 per SD after logit transformation [95% CI, 1.51–2.04]) and CHARGE-AF score (hazard ratio, 1.90 per SD [95% CI, 1.58–2.28]) independently predicted future AF without significant interaction (P=0.54). C statistics were 0.69 (95% CI, 0.66–0.72) for AI-ECG AF model output, 0.69 (95% CI, 0.66–0.71) for CHARGE-AF, and 0.72 (95% CI, 0.69–0.75) for combined AI-ECG and CHARGE-AF score. In the present study, both the AI-ECG AF model output and CHARGE-AF score independently predicted incident AF. The AI-ECG may offer a means to assess risk with a single test and without requiring manual or automated clinical data abstraction. Less

COVID-19 can result in deterioration of cardiac function, which is associated with high mortality. A simple point-of-care diagnostic test to screen for ventricular dysfunction would be clinically useful to guide management. We sought to review the clinical experience with an artificial intelligence Read more

COVID-19 can result in deterioration of cardiac function, which is associated with high mortality. A simple point-of-care diagnostic test to screen for ventricular dysfunction would be clinically useful to guide management. We sought to review the clinical experience with an artificial intelligence electrocardiogram (AI ECG) to screen for ventricular dysfunction in patients with documented COVID-19. We examined all patients in the Mayo Clinic system who underwent clinically indicated electrocardiography and echocardiography within 2 weeks following a positive COVID-19 test and had permitted use of their data for research were included. Of the 27 patients who met the inclusion criteria, one had a history of normal ventricular function who developed COVID-19 myocarditis with rapid clinical decline. The initial AI ECG in this patient indicated normal ventricular function. Repeat AI ECG showed a probability of ejection fraction (EF) less than or equal to 40% of 90.2%, corroborated with an echocardiographic EF of 35%. One other patient had a pre-existing EF less than or equal to 40%, accurately detected by the algorithm before and after COVID-19 diagnosis, and another was found to have a low EF by AI ECG and echocardiography with the COVID-19 diagnosis. The area under the curve for detection of EF less than or equal to 40% was 0.95. This case series suggests that the AI ECG, previously shown to detect ventricular dysfunction in a large general population, may be useful as a screening tool for the detection of cardiac dysfunction in patients with COVID-19. Less

An artificial intelligence-augmented electrocardiogram (AI-ECG) algorithm can identify left ventricular systolic dysfunction (LVSD). We sought to determine whether this AI-ECG algorithm could stratify mortality risk in cardiac intensive care unit (CICU) patients, independent of the presence of LVSD Read more

An artificial intelligence-augmented electrocardiogram (AI-ECG) algorithm can identify left ventricular systolic dysfunction (LVSD). We sought to determine whether this AI-ECG algorithm could stratify mortality risk in cardiac intensive care unit (CICU) patients, independent of the presence of LVSD by transthoracic echocardiography (TTE). We included 11 266 unique Mayo Clinic CICU patients admitted from 2007 to 2018 who underwent AI-ECG after CICU admission. Left ventricular ejection fraction (LVEF) data were extracted for patients with a TTE during hospitalization. Patients with available LVEF data (n = 8242) were divided based on the presence of predicted (by AI-ECG) vs. observed (by TTE) LVSD (defined as LVEF ≤ 35%), using TTE as the gold standard. A stepwise increase in hospital mortality was observed for patients with a true negative, false positive, false negative, and true positive AI-ECG. The AI-ECG prediction of LVSD is associated with hospital mortality in CICU patients, affording risk stratification in addition to that provided by echocardiographic LVEF. Our results emphasize the prognostic value of electrocardiographic patterns reflecting underlying myocardial disease that are recognized by the AI-ECG. Less

Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this Read more

Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD). A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86-0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83-0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76-0.84). The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Less

The primary goal of the initial ECG evaluation of every wide complex tachycardia is to determine whether the tachyarrhythmia has a ventricular or supraventricular origin. The answer to this question drives immediate patient care decisions, ensuing clinical workup, and long-term management Read more

The primary goal of the initial ECG evaluation of every wide complex tachycardia is to determine whether the tachyarrhythmia has a ventricular or supraventricular origin. The answer to this question drives immediate patient care decisions, ensuing clinical workup, and long-term management strategies. Thus, the importance of arriving at the correct diagnosis cannot be understated and has naturally spurred rigorous research, which has brought forth an ever-expanding abundance of manually applied and automated methods to differentiate wide complex tachycardias. In this review, we provide an in-depth analysis of traditional and more contemporary methods to differentiate ventricular tachycardia and supraventricular wide complex tachycardia. In doing so, we: (1) review hallmark wide complex tachycardia differentiation criteria, (2) examine the conceptual and structural design of standard wide complex tachycardia differentiation methods, (3) discuss practical limitations of manually applied ECG interpretation approaches, and (4) highlight recently formulated methods designed to differentiate ventricular tachycardia and supraventricular wide complex tachycardia automatically. Less

Despite many technological advances in the field of cardiology, accurate differentiation of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia continues to be challenging. After decades of rigorous clinical research, a wide variety of Read more

Despite many technological advances in the field of cardiology, accurate differentiation of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia continues to be challenging. After decades of rigorous clinical research, a wide variety of electrocardiographic criteria and algorithms have been developed to provide an accurate means to distinguish these two entities as accurately as possible. Recently, promising automated differentiation methods that utilize computerized electrocardiographic interpretation software have emerged. In this review, we aim to (1) highlight the clinical importance of accurate wide complex tachycardia differentiation, (2) provide an overview of the conventional manually-applied differentiation algorithms, and (3) describe novel automated approaches to differentiate wide complex tachycardia. Less

Patients with moderate to severe aortic stenosis (AS) have increased mortality even when asymptomatic. We hypothesized, that artificial intelligence - (AI) enabled electrocardiogram (ECG) - an inexpensive, ubiquitous, 10 second test - could detect patients with moderate/severe AS. 263,570 Patients Read more

Patients with moderate to severe aortic stenosis (AS) have increased mortality even when asymptomatic. We hypothesized, that artificial intelligence - (AI) enabled electrocardiogram (ECG) - an inexpensive, ubiquitous, 10 second test - could detect patients with moderate/severe AS. 263,570 Patients with an echocardiogram (Echo) and ECG performed within 180 days of each other were included. Patients with past cardiac surgery, or pacemaker implantation prior to the echo were excluded. We trained a convolutional neural network (CNN) to detect AS of at least moderate severity (aortic valve velocity ≥ 3 m/sec and/or area ≤ 1.5 cm2), using a 12 lead ECG. The model that achieved the highest AUC on an internal validation set was selected, and the final performance was assessed on third independent dataset. Of the total cohort, 50% were used for training, 10% for internal validation and 40% for testing the network. Of 105,461 testing patients, 5,088 (4.8%) patients had at least moderate AS and were labeled as “positive”. The area under the receiver operating characteristic curve of the classifier was 0.85 (Fig. 1A). The overall sensitivity, specificity and accuracy were 78%, 75% and 75%, respectively. The predicted probabilities for moderate to severe AS by AI track well with AS progression determined by Echo (Fig. 1B). Adding AI to the 12 lead ECG can permit early detection of AS. The ECG may serve as a powerful tool to screen for asymptomatic aortic stenosis in the community. Less

Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm Read more

Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG. Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine. Less

Hypertrophic cardiomyopathy (HCM) is an uncommon but important cause of sudden cardiac death. This study sought to develop an artificial intelligence approach for the detection of HCM based on 12-lead electrocardiography (ECG). In the combined datasets, mean age was 54.8 ± 15.9 years for the HCM Read more

Hypertrophic cardiomyopathy (HCM) is an uncommon but important cause of sudden cardiac death. This study sought to develop an artificial intelligence approach for the detection of HCM based on 12-lead electrocardiography (ECG). In the combined datasets, mean age was 54.8 ± 15.9 years for the HCM group and 57.5 ± 15.5 years for the control group. After training and validation, the area under the curve (AUC) of the CNN in the validation dataset was 0.95 (95% confidence interval [CI]: 0.94 to 0.97) at the optimal probability threshold of 11% for having HCM. When applying this probability threshold to the testing dataset, the CNN’s AUC was 0.96 (95% CI: 0.95 to 0.96) with sensitivity 87% and specificity 90%. In subgroup analyses, the AUC was 0.95 (95% CI: 0.94 to 0.97) among patients with left ventricular hypertrophy by ECG criteria and 0.95 (95% CI: 0.90 to 1.00) among patients with a normal ECG. The model performed particularly well in younger patients (sensitivity 95%, specificity 92%). In patients with HCM with and without sarcomeric mutations, the model-derived median probabilities for having HCM were 97% and 96%, respectively. ECG-based detection of HCM by an artificial intelligence algorithm can be achieved with high diagnostic performance, particularly in younger patients. This model requires further refinement and external validation, but it may hold promise for HCM screening. Less

This is a case report that includes four of the patient’s standard 12-lead electrocardiograms (ECGs) recorded at different times: baseline ECG, first abnormal ECG identified by the artificial intelligence–enabled ECG (AI-ECG) algorithm, and ECGs performed at the time of the first and second Read more

This is a case report that includes four of the patient’s standard 12-lead electrocardiograms (ECGs) recorded at different times: baseline ECG, first abnormal ECG identified by the artificial intelligence–enabled ECG (AI-ECG) algorithm, and ECGs performed at the time of the first and second thromboembolic events. Notice that all ECGs demonstrate sinus rhythm and are quite similar to each other and relatively unremarkable to the naked eye despite having very different predicted probabilities of concomitant atrial fibrillation (reported in red; abnormal is greater than 8.70%). Retrospective artificial intelligence–enabled electrocardiogram (AI-ECG) analysis of the patient’s available ECGs in our electronic medical record over a 24-year period. Our current algorithm provides an alert to the provider for an abnormal ECG when a likelihood prediction value of greater than 8.70% (dotted red line) is projected. All abnormal ECGs are designated by a red marker in the figure. In this case, the first abnormal ECG would have been reported over 12 years prior to the patient’s first thromboembolic event. The first and second thromboembolic events are circled in black. The black arrows correspond to the ECGs depicted in Figure 1. The red diamond-shaped marker indicates when atrial flutter was recorded (Figure 3). AF = atrial fibrillation. Less

ECG-enabled stethoscopes (ECG-steth) can acquire single lead ECGs during cardiac auscultation, and may facilitate real-time screening for pathologies not routinely identified during physical examination (eg, arrhythmias). The objective of this study was to demonstrate that an AI algorithm trained Read more

ECG-enabled stethoscopes (ECG-steth) can acquire single lead ECGs during cardiac auscultation, and may facilitate real-time screening for pathologies not routinely identified during physical examination (eg, arrhythmias). The objective of this study was to demonstrate that an AI algorithm trained using ECG-12 can be applied to ECG-steth for detection of low EF. Amongst 100 patients (age 70.6±13.8; 61% male), 7 had EF <=35% and 7 had EF 35-50%. The best single recording position was V2 with patient supine (area under the curve [AUC] 0.88 [CI:0.80-0.94] for EF<=35% and 0.81 [CI:0.72-0.88] for EF<50%). When considering best overall lead of all recordings (selected automatically), AUC was 0.906 [CI:0.831-0.955] for EF<=35%; 0.841[CI:0.754-0.906] for EF<50%. In a prospective study, an AI algorithm reliably detected low EF from single lead ECGs acquired using a novel ECG-enabled stethoscope in standard auscultation positions. Less

The accurate differentiation of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular wide complex tachycardia (SWCT) remains problematic despite numerous manually-operated electrocardiogram (ECG) interpretation methods. We sought to create a new WCT differentiation Read more

The accurate differentiation of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular wide complex tachycardia (SWCT) remains problematic despite numerous manually-operated electrocardiogram (ECG) interpretation methods. We sought to create a new WCT differentiation method that could be automatically implemented by computerized ECG interpretation (CEI) software. In a two-part study, we developed and validated a logistic regression model (i.e. WCT Formula) that utilizes computerized measurements and computations derived from patients' paired WCT and subsequent baseline ECGs. In Part 1, a derivation cohort of paired WCT and baseline ECGs was examined to identify independent VT predictors to be incorporated into the WCT Formula. In Part 2, a separate validation cohort of paired WCT and baseline ECGs was used to prospectively evaluate the WCT Formula's diagnostic performance. The derivation cohort was comprised of 317 paired WCT (157 VT, 160 SWCT) and baseline ECGs. A logistic regression model (i.e. WCT Formula) incorporating WCT QRS duration (ms) (p < 0.001), frontal percent amplitude change (%) (p < 0.001), and horizontal percent amplitude change (%) (p < 0.001) yielded effective WCT differentiation (AUC of 0.96). The validation cohort consisted of 284 paired WCT (116 VT, 168 SWCT) and baseline ECGs. The WCT Formula achieved favorable accuracy (91.5%) with strong sensitivity (89.7%) and specificity (92.9%) for VT. The WCT Formula is an example of how contemporary CEI software could be used to successfully differentiate WCTs. The incorporation of similar automated methods into CEI software may improve clinicians' ability to accurately distinguish VT and SWCT. Less

Asymptomatic left ventricular dysfunction (ALVD) is present in 3–6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found. An inexpensive, noninvasive screening tool for ALVD in the doctor’s office is not available. We tested the hypothesis Read more

Asymptomatic left ventricular dysfunction (ALVD) is present in 3–6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found. An inexpensive, noninvasive screening tool for ALVD in the doctor’s office is not available. We tested the hypothesis that application of artificial intelligence (AI) to the electrocardiogram (ECG), a routine method of measuring the heart’s electrical activity, could identify ALVD. When tested on an independent set of 52,870 patients, the network model yielded values for the area under the curve, sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7%, respectively. In patients without ventricular dysfunction, those with a positive AI screen were at 4 times the risk (hazard ratio, 4.1; 95% confidence interval, 3.3 to 5.0) of developing future ventricular dysfunction compared with those with a negative screen. Application of AI to the ECG—a ubiquitous, low-cost test—permits the ECG to serve as a powerful screening tool in asymptomatic individuals to identify ALVD. Less

We have previously used a 12-lead, signal-processed ECG to calculate blood potassium levels. We now assess the feasibility of doing so with a smartphone-enabled single lead, to permit remote monitoring. Twenty-one hemodialysis patients held a smartphone equipped with inexpensive FDA-approved Read more

We have previously used a 12-lead, signal-processed ECG to calculate blood potassium levels. We now assess the feasibility of doing so with a smartphone-enabled single lead, to permit remote monitoring. Twenty-one hemodialysis patients held a smartphone equipped with inexpensive FDA-approved electrodes for three 2min intervals during hemodialysis. Individualized potassium estimation models were generated for each patient. ECG-calculated potassium values were compared to blood potassium results at subsequent visits to evaluate the accuracy of the potassium estimation models. The mean absolute error between the estimated potassium and blood potassium 0.38±0.32 mEq/L (9% of average potassium level) decreasing to 0.6 mEq/L using predictors of poor signal. A single-lead ECG acquired using electrodes attached to a smartphone device can be processed to calculate the serum potassium with an error of 9% in patients undergoing hemodialysis. Less