PROMETHEUS
Research type
Research Study
Full title
Pragmatic, Randomised Observational Multicentre Evaluation of The use of AI in the diagnosis of Heart Disease with Echocardiography USe
IRAS ID
360508
Contact name
Paul Leeson
Contact email
Sponsor organisation
Univeristy of Oxford / Research Governance, Ethics and Assurance
Duration of Study in the UK
2 years, 0 months, 1 days
Research summary
Heart failure is a widespread health issue, affecting 64 million people worldwide. One common type, heart failure with preserved ejection fraction (HFpEF), occurs when the heart struggles to relax and fill with blood properly, even though it pumps normally. This condition can severely impact quality of life, leading to frailty, dependency on caregivers, and frequent hospitalisations.
Echocardiograms, or heart ultrasounds, are critical tools for identifying HFpEF. These scans can reveal key signs, like thickened heart walls or stiff heart tissue, but interpreting these images can be challenging and time-consuming for clinicians. Early and accurate diagnosis of these conditions is essential to ensure patients get the right treatment and avoid serious complications.
Artificial intelligence-powered tools like EchoGo Heart Failure are designed to assist clinicians by analysing echocardiogram images. These systems use advanced AI technology to interpret the images and return diagnostic results directly to the treating clinician. EchoGo Heart Failure can identify signs of the condition based on a single ultrasound image. By providing quick, reliable, and accessible diagnostic support, these tools aim to improve early detection, reduce diagnostic uncertainty, and help clinicians deliver timely and effective care to their patients. In this study, investigators will be asked to review patient clinical scenarios (patient history, clinical symptoms, and echocardiogram imaging) and comment on the likelihood of HFpEF. The investigators will be randomly assigned to either review the patient case with or without the help of AI. At the end of the study, we will check whether or not the use of AI helped the investigators make more accurate decisions on if a patient has HFpEF or not. We will also check if the clinicians are more confident and agree more amongst themselves when they have AI support.
REC name
Yorkshire & The Humber - Sheffield Research Ethics Committee
REC reference
26/YH/0005
Date of REC Opinion
8 Jan 2026
REC opinion
Favourable Opinion