Suffolk doctors lead AI research into early testing of heart problems

Senior doctors hope for a “stimulating” breakthrough in early diagnosis of heart problems using AI technology.

Dr. Simon Radland, a visiting professor at Suffolk University, was the lead author of a study that assesses tests using AI (artificial intelligence) to determine whether people suffer from cardiovascular disease before showing symptoms.

Use 5 electrodes – 4 on the chest and 1 on the back, and return a score of green, amber or red.

This means that unlike traditional 2D ECGs (ECGs), technology measures the electrical activity of the heart in three dimensions.

AI can interpret data such as measuring myocardial rhythm, structure, and perfusion.

The study is hoped to help test people considered to be a high-risk category and help reduce hospital waiting times.

Dr. Rudland, a director of the Suffolk GP Union, was part of a study evaluating Cardisio, a 10-minute test developed in Germany.

“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,” he said.

“To support a patient's diagnosis using digital technology, they have the ability to actually change the path of care, helping to provide a more appropriate or more specific referral to a patient's problem. They also help to start treatment in a primary care setting, rather than putting someone on a waiting list and establishing patients who need to refer them to the hospital.”

Dr. Rudland added that pilots can be held in Suffolk or North Essex for women.

Cardiovascular disease is a condition that affects the heart and blood vessels and can lead to heart attacks, abnormal heart rhythms, and heart failures.

This study focused on asymptomatic adults who are thought to be at risk for cardiovascular disease.

Featuring 628 individual tests, an independent consultant cardiologist reported a strong association between red results and referral to a cardiac clinic.

The data found a positive prediction accuracy of 80% and a negative prediction accuracy of 90.4%, with less than 2% of the tests failing.

A research paper published in the BJGP Open Journal concluded that the test “can access high-risk, hard-to-reach individuals to access tests that are more effective in identifying underlined cardiovascular disease than traditional 12-lead ECGs.”

It was thought that AI could analyze huge amounts of data in ways humans could not.

Earlier this year, Health Secretary Wes Street said the NHS was pushing for the government to “bring analog NHS into the digital age” to “use AI to provide faster and smarter care.”