Doctors could soon use AI to diagnose HEART ATTACKS
>
Doctors could soon use AI to diagnose HEART ATTACKS: algorithm can rule out cardiac events with 99.6% accuracy
- Scientists have developed an algorithm that can reduce the pressure on the emergency room
- It rules out a heart attack in more than double the patient’s rate than current methods
Heart attacks may soon be diagnosed faster and more accurately than ever before thanks to a new AI tool.
Researchers have developed an algorithm that they say can reduce emergency room pressure and reassure patients with chest pain.
A new study suggests that compared to current testing methods, their algorithm was able to rule out a heart attack in more than double the number of patients with an accuracy of 99.6 percent.
The University of Edinburgh team said this ability to quickly rule out a heart attack could significantly reduce hospital admissions and quickly identify patients who can go home safely.
The current gold standard for diagnosing a heart attack involves measuring the levels of the protein troponin in the blood.
Researchers have developed an algorithm they say can reduce pressure on A&E and reassure patients with chest pain (stock image)
But the same threshold is used for each patient, meaning that factors such as age, gender, and other health conditions that affect troponin levels are not taken into account, which affect how accurate a heart attack diagnosis is.
Previous research has shown that women are 50 percent more likely to be misdiagnosed at first, and people who are misdiagnosed are 70 percent more likely to die after 30 days.
The team said their new algorithm, called CoDE-ACS, is an opportunity to avoid this.
It was developed based on data from 10,038 patients in Scotland who arrived in 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 a person has had a heart attack.
The result is presented as a probability score from 0 to 100 for each patient.
Professor Nicholas Mills, who led the study, said: ‘For patients with acute chest pain following a heart attack, early diagnosis and treatment save lives.
“Unfortunately, many conditions cause these common symptoms and diagnosis is not always straightforward.
“Using data and artificial intelligence to support clinical decisions has tremendous potential to improve patient care and efficiency in our busy emergency departments.”
Professor Sir Nilesh Samani, medical director of the British Heart Foundation, which funded the research, said: ‘Chest pain is one of the most common reasons people report to the emergency room.
“Every day, doctors around the world face the challenge of separating patients whose pain is due to a heart attack from those whose pain is due to something less serious.
Figures suggest there are 200,000 hospital visits for heart attacks each year in the UK, while there are about 800,000 each year in the US (stock image)
Developed using advanced data science and AI, CoDE-ACS has the potential to rule in or rule out a heart attack more accurately than current approaches.
“It could be transformative for emergency departments, shortening the time it takes to get a diagnosis, and much better for patients.”
Figures show there are around 100,000 hospital admissions each year in the UK due to heart attacks – the equivalent of one every five minutes.
Clinical trials are now underway in Scotland to assess whether the AI tool can help doctors ease the pressure in overcrowded emergency departments.
The findings were published in the journal Nature Medicine.