Artificial intelligence–enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial

Yao, Xiaoxi; Rushlow, David R.; Inselman, Jonathan; McCoy, Rozalina G.; Thacher, Tom D.; Behnken, Emma; Bernard, Matthew E.; Rosas, Steven L.; Akfaly, Abdulla; Misra, Avanish; Molling, Paul; Krien, Joseph; Foss, Randy; Barry, Bridgette A.; Siontis, Konstantinos C.; Kapa, Suraj; Pellikka, Patricia A.; López-Jiménez, Francisco; Attia, Zachi I.; Shah, Nilay D.; Friedman, Paul A.; Noseworthy, Peter A.

doi:10.1038/s41591-021-01335-4

Cited by 200 publications

(184 citation statements)

References 23 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“… 13 Most recently, a cluster randomised controlled trial made AI-ECG accessible for 12-lead ECG interpretation in a cohort of Mayo Clinic primary care practices, highlighting an increase in the diagnosis of LVEF of 50% or lower (odds ratio [OR] 1·32 (1·01–1·61). 14 …”

Section: Introductionmentioning

confidence: 99%

Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study

Bachtiger

Petri

Scott

et al. 2022

The Lancet Digital Health

View full text Add to dashboard Cite

Summary Background 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. Methods 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. This study is registered with ClinicalTrials.gov , NCT04601415 . Findings 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). Interpretation A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG...

show abstract

Section: Introductionmentioning

confidence: 99%

Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study

Bachtiger

Petri

Scott

et al. 2022

The Lancet Digital Health

View full text Add to dashboard Cite

show abstract

“…AI and machine learning are not yet part of the mainstream and remain at the fringes in clinical decision support for clinicians. Recently researchers at Mayo Clinic reported that the use of their AI-powered decision support tool based on electrocardiogram for predicting a low ejection fraction increased diagnosis of the condition by 32% in the routine primary care setting [ 38 ]. However, the long-term impacts on costs or outcomes have not yet been examined; therefore complete picture still remains elusive.…”

Section: Resultsmentioning

confidence: 99%

Musculoskeletal care – at the confluence of data science, sensors, engineering, and computation

Kataria

Ravindran²

2022

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Data has always been integral to modern medicine in almost all aspects of patient care and the recent proliferation of data has opened up innumerable opportunities for all the stakeholders in trying to improve the quality of care and health outcomes including quality of life and rehabilitation. Greater usage and adoption of digital technologies have led to the convergence of health data in different forms – clinical, self-reported, electronic health records social media, etc. The application and utilization of patient data set continue to get broadened each day with greater availability and access. These are empowering newer cutting-edge solutions such as connected care and artificial intelligence, 3D printing and real-life mimicking prosthetics. The availability of data at micro and macro levels has the potential to act as a catalyst for personalized care based on behavioral, cultural, genetic, and psychological needs for patients with musculoskeletal disorders. Realistic algorithms coupled with biomarkers which can identify relevant interventions and alert the care providers regarding any deterioration. Although in the nascent stage currently, 3D printing, exoskeletons, and virtual rehabilitation hold tremendous potential of cost-effective, precise interventions for the patients.

show abstract

“…Of note, the AI-ECG was recently evaluated in a pragmatic clinical trial and was found to increase the diagnosis of low ejection fraction in the primary care setting. 54 Subsequent plans include prospective studies in pregnant and postpartum women to evaluate the effectiveness of the AI-ECG and its impact on clinical outcomes. With the advent of wearables and smart devices, there is a potential opportunity to obtain personalized ECGs in nonclinical settings.…”

Section: Discussionmentioning

confidence: 99%

Detecting cardiomyopathies in pregnancy and the postpartum period with an electrocardiogram-based deep learning model

Adedinsewo

Johnson

Douglass

et al. 2021

European Heart Journal - Digital Health

Self Cite

View full text Add to dashboard Cite

Aims Cardiovascular disease is a major threat to maternal health, with cardiomyopathy being among the most common acquired cardiovascular diseases during pregnancy and the postpartum period. The aim of our study was to evaluate the effectiveness of an electrocardiogram (ECG)-based deep learning model in identifying cardiomyopathy during pregnancy and the postpartum period. Methods and Results We used an ECG-based deep learning model to detect cardiomyopathy in a cohort of women who were pregnant or in the postpartum period seen at Mayo Clinic. Model performance was evaluated using area under the receiver operating characteristic 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. The study cohort included 1,807 women; 7%, 10%, and 13% had left ventricular ejection fraction (LVEF) of 35% or less, less than 45%, and less than 50%, respectively. The ECG-based deep learning model identified cardiomyopathy with AUCs of 0.92 (LVEF ≤35%), 0.89 (LVEF <45%), and 0.87 (LVEF <50%). For LVEF of 35% or less, AUC was higher in Black (0.95) and Hispanic (0.98) women compared to White (0.91). Natriuretic peptides and the multivariable model had AUCs of 0.85 to 0.86 and 0.72, respectively. Conclusions An ECG-based deep learning model effectively identifies cardiomyopathy during pregnancy and the postpartum period and outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting.

show abstract

Artificial intelligence–enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial

Cited by 200 publications

References 23 publications

Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study

Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study

Musculoskeletal care – at the confluence of data science, sensors, engineering, and computation

Detecting cardiomyopathies in pregnancy and the postpartum period with an electrocardiogram-based deep learning model

Contact Info

Product

Resources

About