London, UK – A groundbreaking clinical trial has demonstrated that an AI-enabled stethoscope can profoundly improve the early detection of three life-threatening heart conditions. The study, a large-scale, real-world trial conducted across the UK, has confirmed the device’s ability to facilitate a more proactive, community-based approach to cardiac care, potentially saving lives and reducing reliance on emergency hospital admissions.
The technology at the heart of this innovation is the Eko DUO, a compact device that marries the traditional digital stethoscope with a single-lead ECG. Developed by Eko Health and utilized by researchers at Imperial College London, the device operates by simultaneously capturing high-fidelity heart sounds and the heart’s electrical signals. These dual data streams are then processed by proprietary AI algorithms, which analyze the complex waveforms for subtle indicators of disease. The entire process, from patient contact to analysis, is completed in under 15 seconds, with results delivered to a clinician’s smartphone.
The TRICORDER Study: A Rigorous and Robust Trial
The findings come from the Triple Cardiovascular Disease Detection with an Artificial Intelligence-enabled Stethoscope (TRICORDER) trial, a pragmatic, two-arm, cluster-randomized controlled study. This robust methodology ensured that the results would be applicable to real-world primary care settings. The trial involved over 12,000 patients across 200 GP surgeries in North West London and North Wales, focusing on individuals with common, non-specific symptoms such as fatigue, breathlessness, and swelling.
The study’s co-primary endpoints were designed to measure not just a higher rate of diagnosis, but also a fundamental shift in the patient care pathway. Researchers sought to determine the difference in:
- The coded incidence of heart failure.
- The ratio of heart failure diagnoses made via community-based care versus those resulting from emergency hospital admission.
The results, as presented at the European Society of Cardiology annual congress, were conclusive. Patients in the intervention group—where GPs had access to the AI stethoscope—were:
- 2.33 times more likely to receive a heart failure diagnosis.
- 3.45 times more likely to be diagnosed with atrial fibrillation (AFib), a leading cause of stroke.
- 1.92 times more likely to be diagnosed with heart valve disease.
Beyond these striking numbers, the study’s success in shifting the diagnostic pathway is a key victory for public health. According to the British Heart Foundation, a significant portion of heart failure cases are only identified during emergency hospital stays, which often means the disease is already at an advanced stage. By enabling earlier detection in a GP’s office, this technology could prevent acute events, improve long-term outcomes, and reduce the massive costs associated with emergency care.
A New Era of Proactive Medicine
While the AI-stethoscope is a powerful tool, it is not a standalone diagnostic. Researchers emphasize that it is a sophisticated triage device. The study showed a notable rate of false positives, where the AI flagged a potential issue that was not confirmed by subsequent testing. This is a deliberate design feature; the tool’s purpose is to be highly sensitive to possible abnormalities, prompting clinicians to refer patients for confirmatory tests like blood work and echocardiograms.
The TRICORDER trial and the Eko DUO represent a significant milestone in bringing advanced diagnostics directly to primary care. The technology’s ability to screen for multiple conditions at the point of care empowers GPs, who are often the first point of contact for patients with cardiac symptoms. This could fundamentally change the patient journey, moving it from a reactive response to a proactive, preventative model.
Journal and Conference Reference
The full results of the TRICORDER study were presented at the European Society of Cardiology (ESC) Congress in Madrid. While a full peer-reviewed paper containing the complete data is expected to be published, the study’s protocol and rationale have been made available in the scientific literature.
Protocol Reference:
Kelshiker, M. A., et al. (2025). Triple cardiovascular disease detection with an artificial intelligence-enabled stethoscope (TRICORDER): design and rationale for a decentralised, real-world cluster-randomised controlled trial and implementation study. BMJ Open, 15(5), e098030. doi:10.1136/bmjopen-2024-098030.
