Feasibility of AI-Guided Handheld Echocardiography for Rheumatic Heart Disease Screening by Non-Cardiologists in Rural Nepal: A Mixed-Methods Diagnostic Accuracy Study

Read the full article See related articles

Listed in

This article is not in any list yet, why not save it to one of your lists.
Log in to save this article

Abstract

Background

Rheumatic heart disease remains a major cause of preventable morbidity and mortality in rural Nepal, where access to cardiovascular specialists and echocardiography is limited. We evaluated the diagnostic accuracy and feasibility of AI-guided echocardiography performed by nurse practitioners for community-based RHD screening.

Methods

We conducted a triangulation mixed-methods study (QUAN > qual) combining a paired cross-sectional diagnostic accuracy study with semi-structured interviews during community screening camps in Damak, Nepal, in November 2025. Nurse practitioners performed AI-guided handheld echocardiography using EchoNous Kosmos Plus devices, with cardiologist overread serving as the comparator. Diagnostic performance was assessed using sensitivity, specificity, and kappa. Interviews were analyzed thematically.

Results

Of 90 participants enrolled, 76 were included in the final analysis. Mean age was 50.8 years, 57.8% were male, and 42.2% had undergone prior cardiac evaluation. Detection of any valvular lesion demonstrated 95.8% sensitivity and 100% specificity, with near-perfect agreement with cardiologist interpretation (κ=0.97). Lesion-specific performance included mitral regurgitation sensitivity 66.7% and specificity 97.3% (κ=0.55), mitral stenosis sensitivity 100% and specificity 97.2% (κ=0.81), aortic regurgitation sensitivity 90.9% and specificity 96.9% (κ=0.84), and tricuspid regurgitation sensitivity and specificity of 100% (κ=1.00). Mean scan duration was 5.8 minutes. Portability, AI-assisted acquisition, and remote review facilitated implementation, while training needs, workflow constraints, and technical issues were barriers.

Conclusions

AI-guided handheld echocardiography performed by nurses demonstrated high diagnostic accuracy and feasibility for rural RHD screening. AI-assisted task-shifting may expand access to early RHD detection in underserved settings.

Article activity feed