An AI tool developed by Ultromics did not reach the same level of correct choices as standard clinical decision-making alone when sending suitable patients for further follow-ups, although the tool could still be useful for less experienced clinicians.
The data, which was presented as part of a Hot Line session at this year’s European Society of Cardiology (ESC) Congress 2024 in London, UK, held between 30 August and 2 September, demonstrated no significant differences in non-inferiority between the two trial arms, the trial’s primary endpoint.
Go deeper with GlobalData
The PROTEUS trial (NCT05028179) investigated the AI software’s ability to correctly augment decision-making in sending patients for invasive coronary angiograms based on stress echocardiography.
Stress echocardiography is one of the most used diagnostic tests for coronary artery disease, but clinician expertise and judgment can affect its accuracy. It is an ultrasound of the heart conducted during rest and activity that determines the risk of heart attack and death in patients with known or suspected coronary artery disease.
The University of Oxford’s Dr Ross Upton and Professor Paul Leeson developed a piece of software, called EchoGo Pro, to help automate the interpretation of images from the scan.
Dr Upton and Professor Leeson co-founded Ultromics, which now claims the software as its product. The US Food and Drug Administration (FDA) has already cleared the technology for the diagnosis of heart failure with preserved ejection fraction in 2022.
How well do you really know your competitors?
Access the most comprehensive Company Profiles on the market, powered by GlobalData. Save hours of research. Gain competitive edge.
Thank you!
Your download email will arrive shortly
Not ready to buy yet? Download a free sample
We are confident about the unique quality of our Company Profiles. However, we want you to make the most beneficial decision for your business, so we offer a free sample that you can download by submitting the below form
By GlobalDataJust over 2,300 patients, all of whom were referred for stress echocardiography for investigation of suspected coronary artery disease, were enrolled in the trial across sites in the UK. The PROTEUS study marked the first time the software was tested in a randomised controlled trial for stress echocardiography use.
While standard clinical decision-making correctly sent 27 out of 36 patients for invasive coronary angiograms, the AI-augmented arm correctly triaged 34 out of 49 referrals.
Dr Upton, also the study’s lead author, said: “Our large, randomised trial involving patients with suspected heart disease from across the UK did not show meaningful differences in the primary endpoint.”
While the data for the primary endpoint was disappointing, Dr Upton stated that further analyses found that AI may benefit decision-making in less experienced clinicians, along with sub-groups of patients whose scans are more difficult to interpret.
Dr Upton, who serves as CEO of Ultromics, added: “The results of this trial suggest that AI has the potential to bring all operators, regardless of experience, up to the same level of accuracy.
“While the PROTEUS trial did not demonstrate meaningful differences in all-comers, the AI diagnostic may also benefit specific subgroups of patients in whom decision-making is known to be more complex.”
Ultromics’ work has caught the eye of Pfizer, who earlier this year partnered with the UK company to advance the AI platform to detect cardiac amyloidosis.
