An algorithm developed with the help of artificial intelligence could soon be used by doctors to diagnose heart attacks, according to new research from the University of Edinburgh, funded by the British Heart Foundation and the National Institute for Health and Care Research and published today in Nature Medicine. greater speed and accuracy than ever before.
The effectiveness of the algorithm called CoDE-ACS [2] was tested on 10,286 patients in six countries. The researchers found that compared to current testing methods, CoDE-ACS was able to rule out heart attacks in more than twice as many patients with 99.6 percent accuracy.
This ability to rule out a heart attack faster than ever before could significantly reduce hospitalizations. Clinical trials are now underway in Scotland, supported by Wellcome Leap, to assess whether the tool can help doctors reduce the pressure on our overcrowded emergency departments.
In addition to quickly ruling out heart attacks in patients, CoDE-ACS could also help doctors identify those whose abnormal troponin levels were due to a heart attack rather than another condition. The AI tool performed well regardless of age, gender or pre-existing medical conditions, showing its potential to reduce misdiagnosis and inequalities in the population.
CoDE-ACS has the potential to make emergency care more efficient and effective by quickly identifying patients who can safely go home and alerting doctors to any who need to stay in hospital for further tests.
The current gold standard for diagnosing a heart attack is to measure troponin protein levels in the blood. But the same threshold is used for each patient. This means that factors such as age, gender and other health problems that affect troponin levels are not taken into account, affecting the accuracy of heart attack diagnosis.
This can lead to inequities in diagnosis. For example, previous research funded by the BHF showed that women are 50 per cent more likely to receive the wrong initial diagnosis. People who are initially misdiagnosed have a 70 percent higher risk of dying after 30 days [3]. The new algorithm is an opportunity to prevent this.
The CoDE-ACS was developed based on data from 10,038 patients in Scotland who presented to hospital with a suspected heart attack. It uses routinely collected patient information such as age, gender, EKG findings and medical history, as well as troponin levels, to predict the likelihood that an individual has had a heart attack. The result is a probability score from 0 to 100 for each patient.
Professor Nicholas Mills, BHF Professor of Cardiology at the Center for Cardiovascular Sciences, University of Edinburgh, who led the research, said:
“For patients with acute chest pain due to a heart attack, early diagnosis and treatment save lives. Unfortunately, many conditions cause these common symptoms, and diagnosis is not always straightforward. The use of data and artificial intelligence to support clinical decisions has enormous potential to improve patient care and efficiency in our busy emergency departments.”
Professor Sir Nilesh Samani, Medical Director of the British Heart Foundation, said:
“Chest pain is one of the most common reasons people come to the emergency department. Every day, doctors around the world face the challenge of separating patients whose pain is caused by a heart attack from those whose pain is caused by something less serious.
“Developed using state-of-the-art data science and artificial intelligence, CoDE-ACS has the potential to identify or rule out a heart attack more accurately than current approaches. It could be transformative for the emergency department, reducing time to diagnosis and much better for patients.”
Read Now:Uddhav Thackeray demand to Rahul Narwekar take a decision on the disqualification of 16 MLAs
