Movement Map

Artificial intelligence software can accurately predict a patient’s risk of heart failure by tracking cardiac movement on MRI scans. The software plots the motion of hundreds of points every second to create an incredibly detailed 3D map of heart function. Here, a model heart rotates with loops that each indicate the direction that a part of the heart moves through as it contracts and relaxes, with red loops moving more quickly than blue. The software then learns to predict patient outcomes using these maps of heart motion. It made accurate predictions about survival 75% of the time and outperformed the manual measurements that doctors currently rely on. The software was applied to 302 people with a heart condition called pulmonary hypertension, and it’s hoped that it will be extended to other causes of heart failure so that doctors and patients can make more informed choices about treatment.

Written by Deborah Oakley

Deborah Oakley

Writer

Deborah is researching healthy cognitive ageing at the University of Cambridge. She previously worked as a science communicator in London, working closely with the BPoD team.

• Video from work by Declan O'Regan and colleagues, Imaging Sciences, MRC LMS
• MRC London Institute of Medical Sciences, London, UK
• Video copyright held by the original authors
• Research published in Nature Machine Intelligence, February 2019