ARTIFICIAL intelligence can diagnose heart attacks faster and more accurately than human doctors, a study found.
Research funded by the British Heart Foundation saw an algorithm accurately rule out heart attack in 99.6 per cent of suspected patients.
It will slash wrong diagnosis rates and get lifesaving treatment to the right patients faster.
Doctors in Scotland are already trialling the system in hospitals.
Professor Nicholas Mills, from the University of Edinburgh, said: “Early diagnosis and treatment saves lives.
“Unfortunately, many conditions cause chest pain and the diagnosis is not always straight forward.
“This has enormous potential to improve care for patients and efficiency in our busy emergency departments.”
There are around 100,000 hospital admissions per year for heart attacks in the UK.
Human doctors judge whether they think someone has had one by testing levels of a blood protein called troponin, which shoots up during an attack.
But results vary and a dangerous result for one patient may be safe for another.
Most read in Health
I was told to lose weight after strangers asked if I was expecting triplets
The 'silent' symptom of high cholesterol in your EYES – and 2 other signs
The six signs of norovirus everyone needs to know
Adding key foods to your diet boosts fitness WITHOUT physical effort, study says
Artificial intelligence considers troponin levels as well as a patient’s age, sex, heartbeat data and medical history – and compares all these to a massive database of past patients.
It then advises the doctor on how likely a heart attack is, by comparing the patient’s results to past sufferers’.
The whole analysis can be done significantly faster by a machine than a person.
Professor Sir Nilesh Samani, medical director at the British Heart Foundation, said: “This has the potential to rule-in or rule-out a heart attack more accurately than current approaches.
“It could be transformational, shortening the time needed to make a diagnosis, which is much better for patients.”
The results of trials of the CoDE-ACS system were published in the journal Nature Medicine.
Source: Read Full Article