The world’s first AI can predict when patients will have a heart attack or stroke better than a DOCTOR
Artificial intelligence has accurately predicted the possibility of a heart attack or stroke in the world’s first.
A study led by Barts Health NHS Trust and University College London used AI to analyze cardiac scans of more than 1,000 patients.
Researchers said it is the first time that blood flow scans that reveal problems with the heart have been read by a computer.
The technology was more accurate in predicting major cardiovascular events within a 19-month follow-up than a doctor who used traditional drugs.
Researchers said it could be used by medical teams to recommend treatments.
Artificial intelligence has accurately predicted the possibility of a heart attack or stroke in the world’s first. It analyzes the scans of patients to measure blood flow
Heart disease is the leading global cause of death and disease, with reduced blood flow a common symptom of many heart conditions.
International guidelines recommend a number of assessments to measure a patient’s blood flow, but many are invasive and carry risks, the study said.
Some non-invasive assessments are available, such as imaging with cardiovascular magnetic resonance (CMR).
This gives a picture of the function and structure of the cardiovascular system, so that doctors can recognize abnormalities.
CMR is validated for detecting coronary artery disease with death and serious adverse events, such as a heart attack, within one year.
But the researchers claim that scan images with this technique are difficult to accurately analyze with the human eye.
Professor James Moon, of Barts Health NHS Trust and University College London, said: ‘Artificial intelligence is moving from computer labs to the real world of healthcare and performing some tasks better than doctors could do alone.
WHAT IS CRUSTAL DISEASE?
Coronary artery disease occurs when the major blood vessels that supply the heart with oxygen and nutrients are damaged.
CAD affects more than 1.6 million men and one million women in the UK and a total of 15 million adults in the US.
It is usually due to plaque and inflammation.
When plaque accumulates, it narrows the arteries, reducing blood flow to the heart.
Over time this can cause angina, while a complete blockage can lead to a heart attack.
Many people initially have no symptoms, but as the plaque builds up, they may notice chest pain or shortness of breath during exercise or stress.
Other causes of CAD are smoking, diabetes and an inactive lifestyle.
It can be prevented by stopping smoking, controlling conditions such as diabetes or high blood pressure, staying active, eating well and controlling stress.
Medications can help lower cholesterol, while aspirin thins the blood to reduce the risk of clots.
In severe cases, stents can be placed in the arteries to open them, while coronary artery bypass surgery creates a graft to bypass the blocked arteries using a vessel from another part of the body.
Source: Mayo Clinic
“We have previously tried to manually measure blood flow, but it is annoying and time-consuming to remove doctors from where they are most needed, with their patients.”
The study was funded by the British Heart Foundation and published in the journal Circulation.
Researchers used CMR scans of more than 1,000 patients, with an average age of 60, at St Bartholomew’s Hospital and Royal Free Hospital.
They had been referred to investigate suspicious and known heart conditions that could be fatal.
The AI technology analyzed the images and immediately quantified the blood flow to the heart.
These measurements were sent to medication teams who can decide on treatment routes.
The predictions were compared with patients’ health outcomes to see if the AI was correct.
Data showed which patients had an important cardiovascular event in a follow-up period of 19 months.
Four percent of the patients died and 16.6 percent suffered from a serious cardiovascular event, such as a heart attack, hospitalization for heart failure or a stroke.
The team discovered that patients with reduced blood flow were more likely to suffer from these adverse health outcomes.
The AI technique had for the first time been able to predict which patients might have health problems related to blood flow.
And it was more accurate than an expert cardiologist who used traditional means.
Researchers say the study is the first time that blood flow scans have been analyzed in this way and can be used by medical teams to recommend treatments.
Dr. Kristopher Knott, of Barts Health NHS Trust and University College London, said: ‘The predictive power and reliability of the AI was impressive and easy to implement in the routine care of a patient.
“The calculations were done while the patients were being scanned and the results were immediately handed over to doctors.
“Because poor blood flow can be treated, these better predictions ultimately lead to better patient care and new insights into how the heart works.”