By Diagnostics World Staff
September 16, 2025 | Results from one of the largest randomized evaluations of AI in routine care showed that an AI-enabled digital stethoscope significantly increased the number of major cardiac conditions detected compared to the standard of care. The study was led by Imperial College London and Imperial College Healthcare NHS Trust and the results were presented last week at the European Society of Cardiology Congress in Madrid.
The TRICORDER (Triple Cardiovascular Disease Detection Using an Artificial Intelligence Smart Stethoscope) study tested Eko Health's AI-enabled digital stethoscope in 205 NHS GP practices with 1.5 million registered patients. More than 12,800 AI-stethoscope exams were performed by nearly 1,000 providers over a 12-month period.
The TRICORDER study was designed to mirror real-world practice. Providers used the device as they would a stethoscope in routine care—at their discretion without patient inclusion or exclusion criteria and without prescriptive oversight. According to the protocol published in BMJ Open in May (DOI: 10.1136/bmjopen-2024-098030), patient and outcome data will be captured from pooled primary and secondary care records and supplemented by qualitative and quantitative clinician surveys.
Using advanced sound technology and ECG sensors, Eko digital stethoscopes capture sounds and electrical signals from the heart, then transmit them to the cloud for AI analysis trained on tens of thousands of patients.
The device connects to an app on the user’s smartphone using Bluetooth connectivity for waveform visualization. Connectivity via cellular/Wi-Fi allows access to cloud-based AI algorithms for analysis of waveforms. No data is stored in the AI stethoscope or user’s smartphone.
The study looked for differences in the detection of heart failure and differences in the ratio of coded incidence of heart failure via hospital admission versus community-based diagnostic pathways.
The findings for using the AI stethoscope were impressive:
- Heart failure was 2.3x more likely to be detected using the AI stethoscope;
- Atrial fibrillation (AFib) was 3.5x more likely to be detected; and
- Valvular heart disease was 1.9x more likely to be detected.
"This is an elegant example of how the humble stethoscope, invented more than 200 years ago, can be upgraded for the 21st century," said Dr. Nicholas S. Peters, Professor of Cardiology and Director of the Health Impact Lab at Imperial College London and senior author on the protocol paper. "By helping GPs identify heart disease in seconds, this technology offers patients earlier access to life-saving treatment, often before symptoms become severe. Demonstrating the benefits of real-world implementation of Eko's device is the real impact of the TRICORDER programme and the mission of The Health Impact Lab"
The findings demonstrate that integration of AI at the point of care can uncover hidden cardiac conditions that might otherwise remain undiagnosed until hospitalization or emergency care.
"The TRICORDER trial confirms what providers worldwide have experienced firsthand. AI can turn a routine exam using a stethoscope into one of the most powerful early detection tools in medicine," said Connor Landgraf, Co-Founder and CEO of Eko Health in a press release. "This is not about future promises; it’s about saving lives today by giving clinicians actionable insights within seconds."
With plans to expand use of Eko AI-enabled digital stethoscopes across practices in South London, Sussex, and Wales, TRICORDER marks a milestone moment in the adoption of AI-powered tools in everyday clinical care.