Researchers in the UK have trained an artificial intelligence (AI) system to assess retinal scans and identify patients prone to a heart attack.
Writing in Nature Machine Intelligence, an international team led by Professor Alex Frangi, University of Leeds, said blockages in retinal blood vessels can indicate similar obstruction elsewhere in the body. Researchers said their system flags individuals prone to myocardial infarction within a year with 70-80% accuracy.
“This technique opens up the possibility of revolutionising the screening of cardiac disease. Retinal scans are comparatively cheap and routinely used in many optician practices. As a result of automated screening, patients who are at high risk of becoming ill could be referred for specialist cardiac services,” said Prof Frangi.
For more, see Quickest way to the heart? Through the eye.
