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

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) dysfunct...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of cardiovascular electrophysiology Jg. 30; H. 5; S. 668 - 674
Hauptverfasser: Attia, Zachi I., Kapa, Suraj, Yao, Xiaoxi, Lopez‐Jimenez, Francisco, Mohan, Tarun L., Pellikka, Patricia A., Carter, Rickey E., Shah, Nilay D., Friedman, Paul A., Noseworthy, Peter A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Wiley Subscription Services, Inc 01.05.2019
Schlagworte:
Algorithms
artificial intelligence
Deep learning
Echocardiography
ejection fraction
EKG
electrocardiogram
Electrocardiography
Heart
Ultrasonic imaging
Ventricle
deep learning
electrocardiogram
ejection fraction
artificial intelligence
echocardiography
ISSN:1045-3873, 1540-8167, 1540-8167
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:Disclosures
In the past 36 months, Dr. Shah has received research support through Mayo Clinic from the Food and Drug Administration to establish Yale‐Mayo Clinic Center for Excellence in Regulatory Science and Innovation (CERSI) program (U01FD005938), from the Centers of Medicare and Medicaid Innovation under the Transforming Clinical Practice Initiative (TCPI), from the Agency for Healthcare Research and Quality (R01HS025164; R01HS025402; 1U19HS024075; and R03HS025517), from the National Heart, Lung and Blood Institute of the National Institutes of Health (NIH) (R56HL130496 and R01HL131535), National Science Foundation, and from the Patient Centered Outcomes Research Institute (PCORI) to develop a Clinical Data Research Network (LHSNet). XY, TLM, PAP, REC, NDS, and PAN report no relevant relationships with industry. Mayo Clinic has licensed use of the low ejection fraction detection algorithm to and electronic stethoscope maker (Eko, Berkeley, CA). Several of the Mayo clinic authors are coinventors in the technology (PAF, SK, FLJ, and ZIA); however, Mayo Clinic and Mayo inventors will not receive financial benefit from the use of the technology at Mayo Clinic.
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Undefined-3
ISSN:1045-3873
1540-8167
1540-8167
DOI:10.1111/jce.13889