An AI-enabled digital stethoscope is a promising tool for earlier VHD diagnosis and intervention.An artificial intelligence (AI)-enabled digital stethoscope outdoes standard-of-care (SoC) analogue auscultation for detecting valvular heart disease (VHD) in a single-arm, single-blinded, prospective study.
Of the 357 participants with risk factors for VHD, 13 had audible structural murmurs (ASM) as confirmed by an echocardiogram and murmur panel. [Eur Heart J Digit Health 2026;7:ztag003]
Six of the ASM cases were correctly identified via SoC auscultation. AI-augmented auscultation correctly identified all but one. These results translated to a significantly higher sensitivity (92.3 percent vs 46.2 percent; p=0.01) but lower specificity (86.9 percent vs 95.6 percent; p<0.001) for the AI-augmented system than for SoC.
For moderate-to-severe VHD confirmed via echocardiography (n=58), AI-augmented auscultation identified 23, whereas SoC identified only eight (sensitivity: 39.7 percent vs 13.8 percent; p=0.01; specificity: 88.6 percent vs 94.7 percent; p<0.001).
Given the significant improvement in point-of-care VHD detection, the AI-enabled digital stethoscope offers a promising tool for earlier diagnosis and intervention in primary care settings, the investigators said.
However, the reduced specificity may increase false positives and subsequent echocardiography referrals, they noted. “While this could contribute to short-term resource use, it must be weighed against the value of earlier detection, particularly in asymptomatic patients who may otherwise progress to advanced disease undiagnosed. We acknowledge this trade-off and emphasize the need for further studies to assess the cost-effectiveness of AI-augmented auscultation in routine care.”
Many undiagnosed cases
VHD symptoms are usually non-specific, and over half of patients with moderate-to-severe disease are asymptomatic. [J Am Coll Cardiol 2016;67:2263-2288] Murmurs are usually an early clinical indicator of underlying VHD. However, cardiac auscultation has only shown a 32–44 percent sensitivity for mild or significant VHD, leaving many patients undiagnosed. [Heart 2018;104:1832-1835]
“This limitation in traditional cardiac auscultation contributes to delayed or missed diagnoses of clinically significant VHD, which can result in rapid disease progression, heart failure, and increased mortality, even in initially asymptomatic patients. More accurate diagnostic methods are therefore of critical importance,” the researchers stressed.
The researchers evaluated 357 patients aged ≥50 years (median age 70 years, 61.9 percent women) at risk for heart disease. The most common VHD risk factors were hypertension (81.8 percent), hyperlipidaemia (70.3 percent), and diabetes (39.5 percent). Participants underwent digital cardiac auscultation by study coordinators followed by AI analysis using an electronic stethoscope, as well as analogue cardiac auscultation by primary care providers.
Implications
The relatively small sample size may not have captured the full range of outcomes across patient subgroups. Moreover, the study was conducted in primary care clinics within the same geographic region, which may limit generalizability of the results.
“Nonetheless, the findings suggest that the implementation of digital stethoscopes with structural murmur detection AI into primary care settings can facilitate earlier detection of previously unrecognized VHD, an essential first step to timely referral, monitoring, and potential intervention,” the researchers said.
Although earlier detection does not guarantee better outcomes, it may help prevent irreversible cardiac damage and reduce long-term morbidity when followed by appropriate management. [Mayo Clin Proc 2025;100:358-379; J Am Coll Cardiol 2019;73:2609-2635; BMJ Open 2025;15:e096538; J Am Coll Cardiol 2024;83:1579-1613]
“[Taken together, the] study provides valuable insights into the clinical impact of a commercially available, novel, and easy-to-use point-of-care solution in a real-world setting,” they concluded.