External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction.


Journal

International journal of cardiology
ISSN: 1874-1754
Titre abrégé: Int J Cardiol
Pays: Netherlands
ID NLM: 8200291

Informations de publication

Date de publication:
15 04 2021
Historique:
received: 19 08 2020
revised: 24 11 2020
accepted: 18 12 2020
pubmed: 6 1 2021
medline: 29 5 2021
entrez: 5 1 2021
Statut: ppublish

Résumé

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.

Sections du résumé

OBJECTIVE
To validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population.
BACKGROUND
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.
METHODS
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.
RESULTS
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.
CONCLUSIONS
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.

Identifiants

pubmed: 33400971
pii: S0167-5273(20)34313-8
doi: 10.1016/j.ijcard.2020.12.065
pmc: PMC7955278
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

130-135

Commentaires et corrections

Type : CommentIn

Informations de copyright

Copyright © 2020. Published by Elsevier B.V.

Déclaration de conflit d'intérêts

Declaration of Competing Interest Mayo Clinic has licensed the underlying technology to EKO, a maker of digital stethoscopes with embedded ECG electrodes. Mayo Clinic may receive financial benefit from the use of this technology, but at no point will Mayo Clinic benefit financially from its use for the care of subjects at Mayo Clinic. P.A.F., F.L.-J., S.K., and Z.I.A. may also receive financial benefit from this agreement.

Références

Card Fail Rev. 2017 Apr;3(1):7-11
pubmed: 28785469
Heart. 2001 Jul;86(1):21-6
pubmed: 11410555
Ann Noninvasive Electrocardiol. 2018 Nov;23(6):e12591
pubmed: 30126010
J Electrocardiol. 2017 Sep - Oct;50(5):620-625
pubmed: 28641860
Heart Int. 2012 Feb 3;7(1):e2
pubmed: 22690295
Am J Cardiol. 1995 Feb 1;75(4):220-3
pubmed: 7832126
J Cardiovasc Electrophysiol. 2019 May;30(5):668-674
pubmed: 30821035
JACC Heart Fail. 2016 Apr;4(4):249-51
pubmed: 26874384
J Card Fail. 2017 Aug;23(8):628-651
pubmed: 28461259
Nat Med. 2019 Jan;25(1):70-74
pubmed: 30617318
N Engl J Med. 2016 Sep 29;375(13):1216-9
pubmed: 27682033
Wellcome Open Res. 2018 Jun 4;3:67
pubmed: 30123849
Stat Med. 2015 May 20;34(11):1912-24
pubmed: 25712874

Auteurs

Itzhak Zachi Attia (IZ)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

Andrew S Tseng (AS)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

Ernest Diez Benavente (ED)

Department of Infection Biology, London School of Hygiene and Tropical Medicine, London WC1E 7HT, UK; Department of Experimental Cardiology, University Medical Center Utrecht, Netherlands.

Jose R Medina-Inojosa (JR)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

Taane G Clark (TG)

Department of Infection Biology, London School of Hygiene and Tropical Medicine, London WC1E 7HT, UK; Department of Infectious Disease Epidemiology, London School of Hygiene & Tropical Medicine, London WC1E 7HT, UK.

Sofia Malyutina (S)

Novosibirsk State Medical University, Russian Ministry of Health, Novosibirsk 630091, Russia; Research Institute of Internal and Preventive Medicine, Branch of Institute of Cytology and Genetics, Siberian Branch of the Russion Academy of Sciences, Novosibirsk 630090, Russia.

Suraj Kapa (S)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

Henrik Schirmer (H)

Department of Community Medicine, UiT The Arctic University of Norway, Tromsø 9037, Norway; Institute for Clinical Medicine, University of Oslo, Campus Ahus, Lørenskog PB 1000 1478, Norway; Department of Cardiology, Akershus University Hospital, 1478 Nordbyhagen, Oslo, Norway.

Alexander V Kudryavtsev (AV)

Northern State Medical University, Arkhangelsk 163000, Russia; Department of Community Medicine, UiT The Arctic University of Norway, Tromsø 9037, Norway.

Peter A Noseworthy (PA)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

Rickey E Carter (RE)

Department of Health Sciences Research, Mayo Clinic, Jacksonville, FL, USA.

Andrew Ryabikov (A)

Novosibirsk State Medical University, Russian Ministry of Health, Novosibirsk 630091, Russia; Research Institute of Internal and Preventive Medicine, Branch of Institute of Cytology and Genetics, Siberian Branch of the Russion Academy of Sciences, Novosibirsk 630090, Russia.

Pablo Perel (P)

Department of Non-communicable Diseases Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London WC1E 7HT, UK.

Paul A Friedman (PA)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.

David A Leon (DA)

Department of Community Medicine, UiT The Arctic University of Norway, Tromsø 9037, Norway; Department of Non-communicable Diseases Epidemiology, Faculty of Epidemiology and Population Health, London School of Hygiene & Tropical Medicine, London WC1E 7HT, UK; International Laboratory for Population and Health, National Research University, Higher School of Economics, Moscow, Russia.

Francisco Lopez-Jimenez (F)

Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA. Electronic address: lopez@mayo.edu.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH