Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.



Coronary artery disease (CAD) is the leading cause of death worldwide and is responsible for over 9 million deaths worldwide and 64,000 deaths annually in the UK. CAD is the leading cause of premature death in the UK, with an annual cost to the economy of over £9 billion. Stress echocardiograpy (SE) is widely available and is a prominent functional imaging test used to diagnose CAD across the UK.

In recent years, AI has been applied to cardiovascular imaging in several different ways and has been shown to produce quicker and less variable outputs than humans alone. The use of AI in the diagnosis of CAD may reduce costs and improve patient outcomes. Ultromics is a spinout company from the University of Oxford that has developed a fully automated AI pipeline of algorithms to mimic the clinical workflow of echocardiography image processing in the diagnosis of CAD. These algorithms are packaged together as the AI software, EchoGo Pro.


We are conducting this trial to identify if the use of EchoGo Pro as a diagnostic support tool provides any benefit at reducing inter-reader variability, increasing accuracy, and thereby improving patient outcomes and reducing health costs. To formally evaluate the impact of EchoGo Pro use on the accuracy of the clinician's decision to make a referral to coronary angiogram following a positive SE, we propose a multi-centre, randomised controlled trial. This trial will compare the provision of an AI-derived report to a clinician against clinician-only standard of care. This will provide the highest level of evidence of any potential benefit or disadvantages prior to the adoption of the software for widespread clinical implementation. Full details of the study can be found here.


PROTEUS looks to recruit 2500 participants who are being referred to SE for the investigation of suspected CAD. These participants will be recruited from 20 NHS hospitals across England encompassing a wide variation of patient demographics and hospital size and experience. Half of the participants will be randomly placed into a group who have their SE reviewed by EchoGo Pro which will provide an AI-derived report to the treating clinician (intervention group), and the other half will have their SE reviewed by their treating clinician alone (control group). 


Participants will be recruited at their routine standard of care appointment where they will be undergoing a stress echocardiogram. Details from their SE procedure will be collected as well as results from EchoGo Pro for those who are placed into the intervention group. Participants will be followed up at both 3 and 6 months following their SE. Members of the local study team will review participant medical notes at each visit to identify if there have been any changes to patient medications or clinical events such as death, myocardial infarction, or referral to invasive coronary angiogram. Also at each follow up visit, participants will be contacted to complete quality of life questionnaires. 


The study is supported with funding from the NIHR/NHSx Artificial Intelligence in Health and Care Award.


The study has been approved by the North West - Preston Research Ethics Committee (Reference 21/NW/0199).