Artificial Intelligence-Powered Left Ventricular Ejection Fraction Analysis Using the LVivoEF Tool for COVID-19 Patients

Ziv Dadon*, Yoed Steinmetz, Nir Levi, Amir Orlev, Daniel Belman, Adi Butnaru, Shemy Carasso, Michael Glikson, Evan Avraham Alpert, Shmuel Gottlieb

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

We sought to prospectively investigate the accuracy of an artificial intelligence (AI)-based tool for left ventricular ejection fraction (LVEF) assessment using a hand-held ultrasound device (HUD) in COVID-19 patients and to examine whether reduced LVEF predicts the composite endpoint of in-hospital death, advanced ventilatory support, shock, myocardial injury, and acute decompensated heart failure. COVID-19 patients were evaluated with a real-time LVEF assessment using an HUD equipped with an AI-based tool vs. assessment by a blinded fellowship-trained echocardiographer. Among 42 patients, those with LVEF < 50% were older with more comorbidities and unfavorable exam characteristics. An excellent correlation was demonstrated between the AI and the echocardiographer LVEF assessment (0.774, p < 0.001). Substantial agreement was demonstrated between the two assessments (kappa = 0.797, p < 0.001). The sensitivity, specificity, PPV, and NPV of the HUD for this threshold were 72.7% 100%, 100%, and 91.2%, respectively. AI-based LVEF < 50% was associated with worse composite endpoints; unadjusted OR = 11.11 (95% CI 2.25–54.94), p = 0.003; adjusted OR = 6.40 (95% CI 1.07–38.09, p = 0.041). An AI-based algorithm incorporated into an HUD can be utilized reliably as a decision support tool for automatic real-time LVEF assessment among COVID-19 patients and may identify patients at risk for unfavorable outcomes. Future larger cohorts should verify the association with outcomes.

Original languageEnglish
Article number7571
JournalJournal of Clinical Medicine
Volume12
Issue number24
DOIs
StatePublished - Dec 2023

Funding

FundersFunder number
Shaare Zedek Medical Center
Shaare Zedek Scientific Ltd.18004712

    Keywords

    • COVID-19
    • artificial intelligence (AI)
    • hand-held echocardiogram
    • left
    • prognosis
    • ventricular function

    Fingerprint

    Dive into the research topics of 'Artificial Intelligence-Powered Left Ventricular Ejection Fraction Analysis Using the LVivoEF Tool for COVID-19 Patients'. Together they form a unique fingerprint.

    Cite this