Study led by University of Suffolk in Ipswich shows AI tests could identify signs of heart diseases before patients show symptoms

Tests using artificial intelligence (AI) could identify signs of heart or blood vessel disease before patients show symptoms, ‘exciting’ new research shows.

A £340,000 study carried out by the University of Suffolk and the University of Wolverhampton, plus a consultant cardiologist from Sandwell and West Birmingham NHS Trust, evaluated Cardisio, a German test, between August 2023 and February 2024.

Cardisio monitors the heart’s electrical activity through electrodes placed on the chest and back, returning a red, amber or green score, before using AI to analyse the data.

The study aimed to look into whether Cardisio could identify cardiovascular diseases without patients showing symptoms and if testing in a community rather than a hospital could help tackle health inequality.

Dr Simon Rudland, from the University of Suffolk, the study’s lead author, said AI could analyse an enormous amount of data, which a human could not get through.

Dr Rudland said: “These are early days, and we need to do more work with more patients to go through the algorithm, but this is an exciting test.

“Using digital technology to support patient diagnosis has the capacity to really change care pathways, helping to make referrals that are more appropriate or more specific to a patient’s problem, as well as initiating treatment in a primary care setting rather than placing someone on a waiting list, and establish which patients need to be referred to hospital.”

In total, 628 individual tests were conducted in ethnically diverse parts of the West Midlands, namely a GP surgery in Handsworth, a pharmacy near Dudley and a community health centre in Quinton.

Those aged 18 and above, who were considered to be at risk of cardiovascular diseases but did not show symptoms, were selected.

An 80 per cent positive predictive accuracy and a 90.4 per cent negative predictive accuracy were recorded in the data, while fewer than two per cent of tests failed.

Strong association between red test results and referral to a cardiology clinic was reported.

In addition, 87.5 per cent of participants recommended the test.

Its authors concluded the test ‘afforded high-risk, hard-to-reach individuals access to a test more effective at identifying underlying cardiovascular disease than a traditional 12-lead electrocardiograms’.

According to the study, Cardisio measured heart activity in three dimensions, rather than the two dimensions used by electrocardiograms, including rhythm, structure and perfusion.

Typically, health professionals have to analyse the data, which can be a tricky job, the university said, while the test could provide clear answers with a larger data pool with higher levels of accuracy.

This could provide a means of testing more patients and ensuring the right people are sent to cardiologists, potentially reducing waiting times, it continued.

According to the researchers, those in rural or ethnically-diverse communities typically do not benefit from early access diagnosis for cardiovascular diseases, being classified as difficult to reach’.

Talks are under way to run a pilot for women living in Suffolk or north Essex, another group which traditionally does not access early diagnosis.

Professor Alan Nevill, from the University of Wolverhampton, who also took part in the study, said: “We believe the implications of this research are huge.

“It means serious illness can be detected quickly and it relieves some of the burden of work on overworked doctors all over the world

“It has been a great privilege to play a role in this research over two years.”

The study was funded by the Small Business Research Initiative and Cardisio, while the report was published in the BJGP Open Journal.