New research shows that using an AI-enabled digital stethoscope more than doubled the identification of moderate to severe valvular heart disease during routine clinical exams, compared to a traditional stethoscope.
The US study, “AI-enabled digital stethoscope improves point-of-care screening for moderate-to-severe valvular heart disease,” was published today (Thursday, February 5, 2026) in European Heart Journal – Digital Health. It shows the AI-assisted tool could help doctors spot patients who might otherwise go undiagnosed.
A total of 357 patients with risk factors for heart disease and aged 50 years or older were evaluated using both a traditional stethoscope and an AI-enabled digital stethoscope in a prospective, single-arm, single-blind study. Participants were recruited from three primary care centers in the same geographic area. the median age of participants was 70 years and 61.9% were women.
The AI stethoscope demonstrated significantly higher sensitivity in detecting heart sound patterns indicative of valvular heart disease with 92.3% sensitivity compared to 46.2% with the traditional stethoscope.
Valvular heart disease can affect more than one in two adults over the age of 65, but often goes undiagnosed by healthcare professionals using a traditional stethoscope in general practice. Valvular heart disease can affect the heart’s function to reduce a person’s ability to perform physical activities and is associated with arrhythmia, heart failure, increased hospitalization, and can be fatal. However, symptoms can be absent, vague or non-specific, meaning many patients do not know they have the condition until it is more advanced.
Dr. Rosalie McDonough, Senior Author, explained the significance of the finding: “Valvular heart disease is unfortunately very common in older adults, yet it often goes undetected until symptoms are advanced. This means patients may experience complications and deterioration of health that could have been avoided with early diagnosis.”
“We showed that an AI-enabled stethoscope is much better at identifying which patients have moderate to severe valvular disease than a traditional stethoscope in real clinical settings. We hope that this technology will allow patients to have faster access to an echocardiogram to formally diagnose their condition and then access treatment faster healthcare.”
The AI-enabled digital stethoscope works by recording high-fidelity heart sounds and applying machine learning algorithms trained to recognize the acoustic patterns associated with valvular heart disease. Traditional methods rely on a healthcare professional using a conventional stethoscope, which in turn relies on the healthcare professional’s own hearing and experience and can be affected by issues such as background noise or time pressure. Patients identified as being at risk for valvular disease in primary care will be referred for diagnosis by echocardiography.
“The use of artificial intelligence provides an additional analytical layer, highlighting abnormalities that may be difficult to detect consistently by ear alone. But the technology does not take over. Using this device requires physicians to use their own clinical judgment,” added Dr. McDonough.
“An additional benefit we observed during the study was that patients assessed with the AI-enabled digital stethoscope appeared more engaged during their appointment. We believe this was because they could see and hear what the clinician was responding to—which may increase trust and engagement with follow-up treatment.”
The study authors noted that the AI-enabled digital stethoscope led to a small decrease in specificity that could potentially increase false-positive results, but suggested that this risk is balanced against the value of earlier detection. They also note that further research will be needed to test the performance of the technology in wider clinical settings and more diverse populations.
“This research adds to a growing body of evidence that AI can augment traditional clinical tools in a practical and responsible way that does not replace healthcare professionals, but gives them tools to have greater confidence in their patient assessment,” Dr McDonough concluded.
Source:
Journal Reference:
