logo
ResearchBunny Logo
Blinded, randomized trial of sonographer versus AI cardiac function assessment

Medicine and Health

Blinded, randomized trial of sonographer versus AI cardiac function assessment

B. He, A. C. Kwan, et al.

Discover the groundbreaking findings of a randomized clinical trial comparing AI with sonographer assessments of left ventricular ejection fraction (LVEF) in echocardiography. Conducted by esteemed researchers including Bryan He and Susan Cheng, this study reveals that AI not only meets the accuracy of sonographers but also shows superiority in mean absolute difference.

00:00
00:00
Playback language: English
Abstract
This blinded, randomized non-inferiority clinical trial (ClinicalTrials.gov ID: NCT01406412) compared AI and sonographer initial assessment of left ventricular ejection fraction (LVEF) in echocardiography. The primary endpoint was the change in LVEF between initial assessment and final cardiologist assessment. The proportion of studies with substantial change ( >5% change) was 16.8% in the AI group and 27.2% in the sonographer group (P<0.001 for non-inferiority and superiority). AI assessment was non-inferior to sonographer assessment and showed superiority in terms of mean absolute difference. The AI-guided workflow was similar for sonographers and cardiologists, and blinding was successful. Initial LVEF assessment by AI was non-inferior to assessment by sonographers.
Publisher
Nature
Published On
Apr 20, 2023
Authors
Bryan He, Alan C. Kwan, Jae Hyung Cho, Neal Yuan, Charles Pollick, Takahiro Shiotai, Joseph Ebinguer, Natalie A. Bello, Janet Wei, Kinari Josan, Grant Duffy, Melvin Jujavarapu, Robert Siegel, Susan Cheng, James Y. Zou, David Ouyang
Tags
AI
echocardiography
left ventricular ejection fraction
sonographer assessment
clinical trial
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny