Show simple item record

dc.contributor.authorAttia, Itzhak Zachi
dc.contributor.authorTseng, Andrew S.
dc.contributor.authorBenavente, Ernest Diez
dc.contributor.authorMedina-Inojosa, Jose R.
dc.contributor.authorClark, Taane
dc.contributor.authorMalyutina, Sofia
dc.contributor.authorKapa, Suraj
dc.contributor.authorSchirmer, Henrik
dc.contributor.authorKudryavtsev, Alexander V
dc.contributor.authorNoseworthy, Peter A.
dc.contributor.authorCarter, Rickey E.
dc.contributor.authorRyabikov, Andrey
dc.contributor.authorPerel, Pablo
dc.contributor.authorFriedman, Paul A.
dc.contributor.authorLeon, David A.
dc.contributor.authorLopez-Jimenez, Francisco
dc.date.accessioned2021-12-22T11:39:50Z
dc.date.available2021-12-22T11:39:50Z
dc.date.issued2021-01-02
dc.description.abstractObjective - To validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population.<p> <p>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.<p> <p>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.<p> <p>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.<p> <p>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.en_US
dc.identifier.citationAttia, Tseng, Benavente, Medina-Inojosa, Clark, Malyutina, Kapa, Schirmer, Kudryavtsev, Noseworthy, Carter, Ryabikov, Perel, Friedman, Leon, Lopez-Jimenez. External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction. International Journal of Cardiology. 2021;329:130-135en_US
dc.identifier.cristinIDFRIDAID 1918148
dc.identifier.doi10.1016/j.ijcard.2020.12.065
dc.identifier.issn0167-5273
dc.identifier.issn1874-1754
dc.identifier.urihttps://hdl.handle.net/10037/23479
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.journalInternational Journal of Cardiology
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.subjectVDP::Medical disciplines: 700::Basic medical, dental and veterinary science disciplines: 710en_US
dc.subjectVDP::Medisinske Fag: 700::Basale medisinske, odontologiske og veterinærmedisinske fag: 710en_US
dc.titleExternal validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunctionen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record