An algorithm developed using artificial intelligence could be used by doctors to diagnose heart attacks with better speed and accuracy, according to new research.
Scientists at the University of Edinburgh found the algorithm, named CoDE-ACS, was able to rule out a heart attack in double the number of patients.
The algorithm was found to be 99.6 per cent accurate.
Researchers hope the algorithm will be able to greatly reduce hospital admissions amid intense pressure on critical care services.
Clinical trials are already underway in Scotland to assess the efficiency of the tool in a hospital setting.
The tool performed well regardless of age, sex or pre-existing health conditions, the study found.
The current gold standard for diagnosing a heart attack is measuring the levels of protonin, a protein, in the blood.
However, the same threshold is used for every patient – meaning factors like age, sex and other health problems are not considered. This can affect the accuracy of a heart attack diagnosis.
Previous research by the British Heart Foundation (BHF) 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 after 30 days.
The algorithm was developed using data from 10,038 patients in Scotland who arrived at hospital with a suspected heart attack.
It uses routinely collected patient information, including age, sex, ECG findings and medical history, as well as troponin levels, to predict the probability that an individual has had a heart attack.
Each patient is then given a probability score of 0 to 100.
Professor Sir Nilesh Samani, Medical Director of the BHF, said the current testing approach made it difficult for clinicians to differentiate a heart attack from something less serious.
“CoDE-ACS, developed using cutting edge data science and AI, has the potential to rule-in or rule-out a heart attack more accurately than current approaches.
“It could be transformational for Emergency Departments, shortening the time needed to make a diagnosis, and much better for patients.”
Professor Nicholas Mills, BHF Professor of Cardiology at the Centre for Cardiovascular Science, University of Edinburgh, who led the research, said: “Harnessing data and artificial intelligence to support clinical decisions has enormous potential to improve care for patients and efficiency in our busy Emergency Departments.”
Analysis by the BHF found that the number of people on cardiac waiting lists has risen to a record high of 380,787 at the end of March 2023 – an increase of nearly 8,000 people since last month.
It means there has been a 63 per cent rise in the cardiac waiting list compared to February 2020, the month before the pandemic began.
