Artificial intelligence (AI) has been used for the first time to instantly and accurately measure blood flow and thus predict chances of death, heart attack and stroke.

In a large study, led by University College London (UCL) and Barts Health NHS Trust and funded by the British Heart Foundation, researchers took routine cardiovascular magnetic resonance (CMR) scans from 1,000 patients and used AI to analyse the images.

The AI allowed the researchers to precisely and instantaneously quantify the blood flow to the heart muscle and deliver the measurements to the medical teams treating the patients.

Comparing the AI-generated blood flow results with the health outcomes of each patient allowed the team to establish that the patients with reduced blood flow were more likely to have adverse health outcomes. These included death, heart attack, stroke and heart failure.

The AI was able to predict which patients would die or suffer adverse events better than a doctor would be able to do alone, the team said.

UCL professor of cardiology James Moon 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.”

The technology could be used by clinicians to help recommend treatments to improve a patient’s blood flow.

Heart disease is the leading global cause of death and illness, and the treatable symptom of reduced blood flow accompanies many heart conditions.

Tests to measure a patient’s blood flow can be high-risk and invasive, and non-invasive assessments like CMR imaging can be incredibly difficult to analyse with precision.

UCL professor of cardiology Dr Kristopher Knott 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.”

The study has been published in the journal Circulation.