Usher Institute

AI tool could improve heart attack diagnosis

An algorithm developed using artificial intelligence could soon be used by doctors to diagnose heart attacks with better speed and accuracy than ever before.

Compared to current testing methods, the algorithm was able to rule out a heart attack in more than double the number of patients, with an accuracy of 99.6 per cent.

The ability to quickly rule out a heart attack could greatly reduce hospital admissions, preventing further pressure on emergency departments, experts say.

Accurate diagnosis

The effectiveness of the algorithm, named CoDE-ACS, was tested on 10,286 patients in six countries around the world.

As well as quickly ruling out heart attacks in patients, CoDE-ACS could also help doctors to identify those whose high troponin levels – a protein in the blood often raised following a heart attack – were due to a heart attack rather than another condition.

Developed by researchers at the University of Edinburgh, the AI tool performed well regardless of age, sex, or pre-existing health conditions, showing its potential for reducing misdiagnosis and inequalities across the population.

Experts say CoDE-ACS has the potential to make emergency care more efficient and effective, by rapidly identifying patients that are safe to go home, and by highlighting to doctors those who need to stay in hospital for further tests.

Reduce inequalities

The current best way to diagnose a heart attack is measuring levels of the protein troponin in the blood. But the same threshold is used for every patient.

This means that factors like age, sex and other health problems that influence troponin levels are not considered, affecting the accuracy of heart attack diagnoses. This can lead to inequalities in diagnosis.

Previous research has shown that women are 50 per cent more likely to get a wrong initial diagnosis. People who are initially misdiagnosed have a 70 per cent higher risk of dying. The new algorithm is an opportunity to prevent this, experts say.

CoDE-ACS was developed using data from patients in Scotland who arrived at hospital with a suspected heart attack.

It uses routinely collected patient information, such as age, sex, ECG findings and medical history, as well as troponin levels, to predict the probability that an individual has had a heart attack. The result is a probability score from 0 to 100 for each patient.

Clinical applications

Clinical trials are now underway in Scotland with support from the Wellcome Leap to assess whether the tool can help doctors reduce pressure on the country’s overcrowded emergency departments.

The intellectual property underpinning the CoDE-ACS algorithm has been developed and protected with support from the University’s commercialisation service, Edinburgh Innovations.

The study, published in Nature Medicine, was led by the University of Edinburgh and funded by the British Heart Foundation and the UK’s National Institute for Health and Care Research.

For patients with acute chest pain due to a heart attack, early diagnosis and treatment saves lives. Unfortunately, many conditions cause these common symptoms, and the diagnosis is not always straight forward. Harnessing data and artificial intelligence to support clinical decisions has enormous potential to improve care for patients and efficiency in our busy emergency departments.

Professor Nicholas MillsBHF Professor of Cardiology at the Centre for Cardiovascular Science, University of Edinburgh, and study lead

We are proud to be supporting Nick and his team as they take their research and invention out of the University and into clinical settings where it can really make a difference to healthcare outcomes.

Dr John LonsdaleHead of Enterprise at Edinburgh Innovations

Data-Driven Innovation

Professor Nicholas Mills, study lead, is Senior Responsible Officer for the Health and Social Care Data-Driven Innovation Programme at the Usher Institute.

Related links

Read the paper in the journal Nature Medicine

View the CoDE-ACS app

Health and Social Care Data-Driven Innovation