Washington: According to new investigation from the University of Edinburghfunded by the British Heart Foundation and the National Institute for Health and Care Investigationand published today in Nature Medicine, an algorithm developed using artificial intelligence it could soon be used by doctors to diagnose heart attacks more quickly and accurately than ever before.
The effectiveness of the algorithm, called CODE-ACS, was tested in 10,286 patients in six countries around the world. The researchers found that, compared to current testing methods, CODE-ACS could rule out one myocardial infarction in more than twice the number of patients, with an accuracy of 99.6 percent.
This ability to rule out a heart attack faster than ever could greatly reduce hospital admissions. Clinical trials are now underway in Scotland with support from Wellcome Leap, to test 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 тАЛтАЛtool worked well regardless of age, gender, or pre-existing health conditions, demonstrating its potential to reduce misdiagnosis and inequities in the population.
CoDE-ACS has the potential to make emergency care more efficient and effective by quickly identifying patients who are safe to go home and flagging to physicians those who need to remain in hospital for further evidence.
The current gold standard for diagnosing a heart attack is to measure levels of the protein troponin in the blood. But the same threshold is used for all patients. This means that factors such as age, gender and other health issues that affect troponin levels are not taken into account, thus affecting the accuracy of myocardial infarction diagnoses.
This can lead to misdiagnosis. For example, previous BHF-funded research has shown that women are 50 percent more likely to receive an initial incorrect diagnosis. People who are initially misdiagnosed have a 70 percent increased risk of dying after 30 days. The new algorithm is an opportunity to prevent this.
CoDE-ACS was developed using data from 10,038 patients in Scotland who had come to hospital with a suspected heart attack. It uses routinely collected patient information, such as age, gender, ECG findings, and medical history, as well as troponin levels, to predict the likelihood that a person 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 Edinburghwho led the investigation, said:
“For patients with acute chest pain due to heart attack, early diagnosis and treatment saves lives. Unfortunately, many conditions cause these common symptoms, and diagnosis is not always straightforward. Leveraging 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 present to emergency departments. Every day, physicians around the world face the challenge of separating patients whose pain is due to heart attack those whose pain is due to something less serious.
“CoDE-ACS, developed using cutting-edge data science and artificial intelligence, has the potential to confirm or rule out a heart attack with greater precision than current approaches. It could be transformative for emergency departments, shortening the time it takes to make a diagnosis, and much better for the patients.
