Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram

Attia, Zachi I.; Kapa, Suraj; López-Jiménez, Francisco; McKie, Paul M.; Ladewig, Dorothy J.; Satam, Gaurav; Pellikka, Patricia A.; Enríquez-Sarano, Maurice; Noseworthy, Peter A.; Munger, Thomas M.; Asirvatham, Samuel J.; Scott, Christopher G.; Carter, Rickey E.; Friedman, Paul A.

doi:10.1038/s41591-018-0240-2

Cited by 875 publications

(662 citation statements)

References 31 publications

Supporting

Mentioning

635

Contrasting

Unclassified

Order By: Relevance

“…As previously described, a convolutional neural network (CNN) trained with Keras with a Tensorflow (Google, Mountain View, CA) backend was developed and validated. This study used the previous algorithm with no additional training or optimization . The only model input reported was a 12‐lead ECG.…”

Section: Methodsmentioning

confidence: 88%

“…We previously reported on the development of this algorithm in a large population of patients with paired ECGs and echocardiograms . However, the current study extends this evaluation to the patient not otherwise undergoing echocardiography and is the first to report the rate of “new positive screens.” We observed an overall new positive screen rate of 3.5%, but this was highly age dependent and ranged from 1.6% for ages 20 to 25 years to more than 10% for ages 95 years above.…”

Section: Discussionmentioning

confidence: 99%

“…This study used the previous algorithm with no additional training or optimization. 5 The only model input reported was a 12-lead ECG. Each 12-lead ECG was a matrix with 12 × 5000 matrix (ie, 12 leads by 10 seconds duration sampled at 500 Hz) divided to 2 seconds segments with an overlap of 1 second.…”

Section: Overview Of Ai Modelmentioning

confidence: 99%

“…We recently reported on the development of a deep learning algorithm for the detection of LV systolic dysfunction using the routine 12-lead electrocardiogram (ECG). 5 In a large retrospective cohort, the algorithm had favorable performance characteristics (area under the curve [AUC] was 0.93; sensitivity, 86.3%; specificity, 85.7%; and accuracy, 85.7%) for detecting EF less than or equal to 35%. The algorithm could be used to facilitate a noninvasive, low-cost approach to screen asymptomatic patients for the presence of unrecognized LV dysfunction during routine electrocardiography.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction

Attia

Kapa

Yao

et al. 2019

Cardiovasc electrophysiol

Self Cite

124

View full text Add to dashboard Cite

Objectives We sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12‐lead electrocardiogram (ECG) in a large prospective cohort. Background Patients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging. Methods We applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new “positive screens.” Results Among 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 “false‐positives screens,” 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT‐pro‐BNP after the initial “positive screen.” Conclusions A deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.

show abstract

Section: Methodsmentioning

confidence: 88%

Section: Discussionmentioning

confidence: 99%

Section: Overview Of Ai Modelmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction

Attia

Kapa

Yao

et al. 2019

Cardiovasc electrophysiol

Self Cite

124

View full text Add to dashboard Cite

show abstract

“…20 A network model using an AI-enabled electrocardiogram was successful in screening patients for asymptomatic left ventricle dysfunction. 21 The integration of AI technology and biosensors with the wireless capabilities through Bluetooth, Wi-Fi, and global positioning systems have led to the development of pointof-care (POC) diagnosis. POC, which represents fast, cheap, and effective processes to diagnose conditions by bringing a health expert or laboratory to a patient's home, has a huge influence on the quality of care and health care costs in developing countries.…”

Section: Central Messagementioning

confidence: 99%

Wireless monitoring and artificial intelligence: A bright future in cardiothoracic surgery

Kalfa

Agrawal

Goldshtrom

et al. 2020

The Journal of Thoracic and Cardiovascular Surgery

View full text Add to dashboard Cite

show abstract

Use of Artificial Intelligence and Deep Neural Networks in Evaluation of Patients With Electrocardiographically Concealed Long QT Syndrome From the Surface 12-Lead Electrocardiogram

Bos

Attia

Albert³

et al. 2021

JAMA Cardiol

Self Cite

View full text Add to dashboard Cite

IMPORTANCELong QT syndrome (LQTS) is characterized by prolongation of the QT interval and is associated with an increased risk of sudden cardiac death. However, although QT interval prolongation is the hallmark feature of LQTS, approximately 40% of patients with genetically confirmed LQTS have a normal corrected QT (QTc) at rest. Distinguishing patients with LQTS from those with a normal QTc is important to correctly diagnose disease, implement simple LQTS preventive measures, and initiate prophylactic therapy if necessary.OBJECTIVE To determine whether artificial intelligence (AI) using deep neural networks is better than the QTc alone in distinguishing patients with concealed LQTS from those with a normal QTc using a 12-lead electrocardiogram (ECG). DESIGN, SETTING, AND PARTICIPANTSA diagnostic case-control study was performed using all available 12-lead ECGs from 2059 patients presenting to a specialized genetic heart rhythm clinic. Patients were included if they had a definitive clinical and/or genetic diagnosis of type 1, 2, or 3 LQTS (LQT1, 2, or 3) or were seen because of an initial suspicion for LQTS but were discharged without this diagnosis. A multilayer convolutional neural network was used to classify patients based on a 10-second, 12-lead ECG, AI-enhanced ECG (AI-ECG). The convolutional neural network was trained using 60% of the patients, validated in 10% of the patients, and tested on the remaining patients (30%). The study was conducted from January 1, 1999, to December 31, 2018. MAIN OUTCOMES AND MEASURESThe goal of the study was to test the ability of the convolutional neural network to distinguish patients with LQTS from those who were evaluated for LQTS but discharged without this diagnosis, especially among patients with genetically confirmed LQTS but a normal QTc value at rest (referred to as genotype positive/phenotype negative LQTS, normal QT interval LQTS, or concealed LQTS). RESULTSOf the 2059 patients included, 1180 were men (57%); mean (SD) age at first ECG was 21.6 (15.6) years. All 12-lead ECGs from 967 patients with LQTS and 1092 who were evaluated for LQTS but discharged without this diagnosis were included for AI-ECG analysis. Based on the ECG-derived QTc alone, patients were classified with an area under the curve (AUC) value of 0.824 (95% CI, 0.79-0.858); using AI-ECG, the AUC was 0.900 (95% CI, 0.876-0.925). Furthermore, in the subset of patients who had a normal resting QTc (<450 milliseconds), the QTc alone distinguished those with LQTS from those without LQTS with an AUC of 0.741 (95% CI, 0.689-0.794), whereas the AI-ECG increased this discrimination to an AUC of 0.863 (95% CI, 0.824-0.903). In addition, the AI-ECG was able to distinguish the 3 main genotypic subgroups (LQT1, LQT2, and LQT3) with an AUC of 0.921 (95% CI, 0.890-0.951) for LQT1 compared with LQT2 and 3, 0.944 (95% CI, 0.918-0.970) for LQT2 compared with LQT1 and 3, and 0.863 (95% CI, 0.792-0.934) for LQT3 compared with LQT1 and 2.CONCLUSIONS AND RELEVANCE In this study, the AI-ECG was found to distinguish pati...

show abstract

Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram

Cited by 875 publications

References 31 publications

Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction

Prospective validation of a deep learning electrocardiogram algorithm for the detection of left ventricular systolic dysfunction

Wireless monitoring and artificial intelligence: A bright future in cardiothoracic surgery

Use of Artificial Intelligence and Deep Neural Networks in Evaluation of Patients With Electrocardiographically Concealed Long QT Syndrome From the Surface 12-Lead Electrocardiogram

Contact Info

Product

Resources

About