External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction.
Artificial intelligence
Electrocardiogram
Left ventricular systolic dysfunction
Machine learning
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
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
130-135Commentaires 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