An AI stethoscope found serious heart conditions earlier and more often in GP practices, a large NHS study reported.
When doctors used it as intended, it detected heart failure, when the heart cannot pump blood effectively, arrhythmias, abnormal heart rhythms, and valve disease more quickly and more often.
However, it did not significantly increase overall heart failure diagnoses because many GPs did not use the device consistently in routine practice.
Dr Patrik Bachtiger, one of the researchers who led the study, said: “Our trial suggests AI tools like smart stethoscopes help us detect heart conditions earlier, but only if they are used and properly integrated into everyday clinical practice.
“Although the technology performed well, the impact it could have in the real world depends on doctors being able to use the technology easily during busy clinics.”
The clinical trial, called TRICORDER, was led by researchers at Imperial’s National Heart and Lung Institute and Imperial College Healthcare NHS Trust, and supported by the Imperial Biomedical Research Centre.
The study involved 205 NHS GP practices and more than 1.5m registered patients in the UK.
Over the year-long study, doctors performed nearly 13,000 AI-assisted heart examinations.
Patients examined with the device had higher detection rates, with nearly twice as many new heart failure cases and three times as many detections of irregular heart rhythms compared with patients who were not examined with it.
Conditions such as heart failure, irregular heart rhythms and valve problems are common and treatable, but are often only diagnosed after an emergency hospital visit.
Researchers said AI-enabled stethoscopes could help doctors spot these problems earlier during routine appointments.
Co-lead author Dr Mihir Kelshiker said: “Some practices used the device less over time because it added extra steps to routine care and was not well integrated with existing electronic health record systems.
“Despite its diagnostic accuracy, it was these practical barriers that limited the overall impact of the technology.”
Professor Nicholas Peters, who led the team, added: “Studies like this are essential for patients, health systems, industry, regulators and researchers to bring the most promising health innovations into routine patient care.”
