An AI to diagnose heart attacks

Doctors could soon use an AI algorithm to diagnose heart attacks with better speed and accuracy, according to new research by the University of Edinburgh, funded by the British Heart Foundation and the National Institute for Health and Care Research.

The algorithm named CoDe-ACS was tested on 10,286 patients across six countries.

The research discovered that the algorithm was able to rule out a heart attack in more than double the number of patients, with a 99.6% accuracy, in comparison to current testing methods.

The results mean that hospital admissions could be greatly reduced with the ability to rule out a heart attack more efficiently, and clinical trials are now underway in Scotland to test this.

CoDE-ACS may also help doctors identify patients whose abnormal troponin levels were due to a heart attack rather than another condition (troponin proteins are released in the blood when the heart muscle has been damaged).

Usually, diagnosing a heart attack is done so by measuring the levels of protein troponin in the blood, but is measured at the same level for any patient regardless of age, sex, or pre-existing health conditions.

This equal measurement can lead to inequalities in diagnosis. As it stands, 50% of women are more likely to get a wrong initial diagnosis, and those who are initially misdiagnosed have a 70% higher risk of dying after 30 days.

According to the research, CoDE-ACS is an opportunity to prevent this, as it performed well regardless of age, sex, or pre-existing health conditions.

Professor Nicholas Mills, BHF Professor of Cardiology at the Centre for Cardiovascular Science, University of Edinburgh, who led the research, said: “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,” Mills added.

3D software design company Dassault Systèmes has developed a 3D platform that can map out the mechanics of heart operatations and enable paediatricians and cardiologists to plan the best course of action to correct its faults.

A patient who has just had a heart attack, for instance, can have a monitor placed on their chest with the data then sent to their virtual twin. They can wear a VR headset and understand what’s happening, as a lay person, in real time.