New AI Can Predict When Patients Will Have Heart Attack or Stroke

A study led by Barts Health NHS Trust and University College London used AI to analyses cardiac scans of more than 1,000 patients, DailyMail reported.

Researchers said it's the first time blood flow scans, which reveal problems with the heart, have been read by a computer.

The technology was more accurate at predicting major cardiovascular events within a 19-month follow-up than a doctor using traditional means.

Researchers said it could be used by medical teams to recommend treatments.

Heart disease is the leading global cause of death and illness, 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 risk, the study said.

Some non-invasive assessments are available, such as Cardiovascular Magnetic Resonance (CMR) imaging.

This provides an image of the function and structure of the cardiovascular system, allowing doctors to spot abnormalities.

CMR has been validated for detecting coronary artery disease with death and major adverse events, such as heart attack, within a year.

But the researchers argue scan images using this technique are difficult to analyze in a precise manner with the human eye.

Professor James Moon, from Barts Health NHS Trust and University College London, said: 'Artificial intelligence is moving out of the computer labs and into the real world of healthcare, carrying out some tasks better than doctors could do alone.

'We have tried to measure blood flow manually before, but it is tedious and time-consuming, taking doctors away from where they are needed most, with their patients.'

Researchers used CMR scans from more than 1,000 patients, with an average age of 60, at St Bartholomew's Hospital and the Royal Free Hospital.

They had been referred to investigate suspected and known heart conditions which could be deadly.

The AI technology analyzed the images and instantly quantified blood flow to the heart.

These measurements were sent to medicals teams who can decide on treatment pathways.

The predictions were compared with the health outcome of patients to see if the AI was correct.

Data revealed which patients had gone on to have a major cardiovascular event in a follow-up period of 19 months.

Four per cent of the patients died, and 16.6 per cent suffered a major cardiovascular event, such as a heart attack, heart failure hospital admission or stroke.

The team found that the patients with reduced blood flow were more likely to have these adverse health outcomes.

The AI technique had, for the first time, been able to predict which patients might suffer health issues related to blood flow.

And it was more accurate than an expert cardiologist using traditional means.

say the study is the first time blood flow scans have been analyzed in this way and could be used by medical teams to help recommend treatments.

Dr Kristopher Knott, from Barts Health NHS Trust and University College London, said: 'The predictive power and reliability of the AI was impressive and easy to implement within a patient's routine care.

'The calculations were happening as the patients were being scanned, and the results were immediately delivered to doctors.

'As poor blood flow is treatable, these better predictions ultimately lead to better patient care, as well as giving us new insights into how the heart works.'