Cardiology in Review · 20 Nov 2026
Diagnostic Accuracy of Artificial Intelligence–Enabled Cardiac Auscultation for Detecting Clinically Significant Valvular Heart Disease: A Systematic Review and Meta-Analysis
Humza Saeed, Tameem Bin Nasir, Ayesha Rehman, Uzair Majeed, Ishtiaq Hussain, Salman Khalid, Naeem Khan Tahirkheli
Citations by database
Each database indexes a different set of journals, preprints and books, so they are shown side by side rather than blended.
- OpenCitations0
- Crossref0
- Europe PMC0
Citations per year
The current year is still counting.
- 2026 so far0
Abstract
Early identification of clinically significant valvular heart disease (VHD) remains challenging because echocardiography is resource-intensive and conventional auscultation is operator-dependent. Artificial intelligence (AI)-enabled analysis of digital heart sounds has emerged as a promising screening strategy, but its overall diagnostic performance has not been systematically evaluated. We conducted a Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy studies–compliant systematic review and diagnostic test accuracy meta-analysis of studies evaluating AI-enabled cardiac auscultation against transthoracic echocardiography for detecting clinically significant VHD, defined according to each study’s echocardiographic criteria. MEDLINE, Embase, and CENTRAL were searched through July 2026, and pooled sensitivity, specificity, summary receiver operating characteristic area under the curve, diagnostic odds ratio, and accuracy were estimated using random-effects models. Eight studies comprising 4374 analyzed participants were included. AI-enabled cardiac auscultation demonstrated a pooled sensitivity of 72% (95% CI 54–85%) and specificity of 82% (95% CI 74–88%) for detecting clinically significant VHD. The summary receiver operating characteristic area under the curve was 0.814 (95% CI 0.569–0.888), and the pooled diagnostic odds ratio was 11.39 (95% CI 3.76–34.47), corresponding to positive and negative likelihood ratios of approximately 4.0 and 0.34, respectively. Overall pooled diagnostic accuracy was 78% (95% CI 67–86%). Subgroup analyses demonstrated substantially higher sensitivity for studies evaluating isolated aortic stenosis than composite VHD (92% vs. 55%; P < 0.001), whereas specificity was comparable. AI-enabled cardiac auscultation demonstrates promising diagnostic performance for identifying clinically significant VHD and may serve as a front-line screening tool to prioritize patients for echocardiography. Future prospective multicenter studies using standardized recording protocols and external validation are needed before widespread clinical implementation.
What the data shows
- No database records a citation yet, as is usual for a paper this new.
Graph
This paper in the middle, its authors and their most-cited papers below, the papers it cites to the left and the papers citing it to the right. The timeline lays every paper out by year.
Select a node for its details. Drag to pan, scroll to zoom, drag a node to move it.
Start with
Cited by 0 papers
Who cites this paper, from open citation data, with Crossref's record of each; the 100 newest when there are more.
References (25)
What it cites, from open citation data, with Crossref's record of each.
Sign in to see 5 more references
A free account opens the rest of the citing papers and references on every paper’s page.