AI to enhance understanding of heart attacks and stroke


New research led by UCL and Barts Health NHS Trust have for the first time used artificial intelligence to accurately measure blood flow.

The findings of the study have been able to predict chances of heart attack, stroke and death. Furthermore, the new technique can also be used by doctors to recommend treatments in order to further improve patient’s blood flow, since reduced blood flow has been recognized as a significant symptom for several heart conditions.

It has been a challenge to analyse scan images precisely which has further made it difficult to recommend treatment and prognosis.

The recent study has been the first of its kind funded by British Heart Foundation. Based on the study researchers evaluated routine CMR scans from more than 1000 patients attending St Bartholomew’s Hospital and the Royal Free Hospital. They further used a new automated artificial intelligence technique to study these images.

The method helped to accurately quantify blood flow to heart muscle and hence deliver the measurements to medical teams for treatment of patients.

The AI- generated blood flow results proved that patients with reduced blood flow had more adverse health outcomes including stroke, heart failure and heart attack.

Professor James Moon (UCL Institute of Cardiovascular Science and Barts Health NHS Trust) commented on the latest development, “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.”