Key result
View-agnostic deep learning detects LVEF ≤40% from handheld ultrasound with ~0.98 AUC.
Why the study?
Echocardiography requires experienced operators for specific viewing angles, limiting clinical decision-making for handheld cardiac ultrasound collected by novice users.
Does a view-agnostic deep learning framework accurately estimate LVEF, age, and sex from echocardiography regardless of view or user expertise?
Observational (n=33,924)
Yes
Does a view-agnostic deep learning framework accurately estimate LVEF, age, and sex from echocardiography regardless of view or user expertise?
Answers are grounded in this paper and cite their sources.
A view-agnostic deep learning framework can accurately estimate LVEF, age, and sex from echocardiograms, performing well even on handheld ultrasound images acquired by novice users.
Echocardiography traditionally requires experienced operators to select and interpret clips from specific viewing angles. Clinical decision-making is therefore limited for handheld cardiac ultrasound (HCU), which is often collected by novice users. In this study, we developed a view-agnostic deep learning framework to estimate left ventricular ejection fraction (LVEF), patient age, and patient sex from any of several views containing the left ventricle. Model performance was: (1) consistently strong across retrospective transthoracic echocardiography (TTE) datasets; (2) comparable between prospective HCU versus TTE (625 patients; LVEF r 2 0.80 vs. 0.86, LVEF [> or ≤40%] AUC 0.981 vs. 0.993, age r 2 0.85 vs. 0.87, sex classification AUC 0.985 vs. 0.996); (3) comparable between prospective HCU data collected by experts versus novice users (100 patients; LVEF r 2 0.78 vs. 0.66, LVEF AUC 0.982 vs. 0.966). This approach may broaden the clinical utility of echocardiography by lessening the need for user expertise in image acquisition.
No takes yet. Share an insight, caveat, or question.
Anisuzzaman et al. (2025) conducted an observational in Echocardiography analysis (n=33,924). View-agnostic deep learning framework vs. Clinical reference standard (expert sonographer TTE) was evaluated on Detection of left ventricular ejection fraction ≤40% using handheld cardiac ultrasound (AUC 0.981). A view-agnostic deep learning framework accurately estimated left ventricular ejection fraction from handheld cardiac ultrasound images, achieving an AUC of 0.981 for detecting LVEF ≤40%.
Synapse has enriched 10 related papers. Consider them for comparative context: