Computers have learnt to predict survival probability in patients with a heart condition.<\/p>\n
This may help doctors identify patients at greatest risk of death earlier and treat them straight away.<\/p>\n
\u201cThis is the first time computers have interpreted heart scans to accurately predict how long patients will live,\u201d said Declan O\u2019Regan of the MRC London Institute of Medical Sciences<\/strong><\/a>.<\/p>\n \u201cThe computer is up to 80% accurate at predicting survival at one year. A doctor equipped with this new cardiac imaging approach would be able to make more informed judgements.”<\/p>\n The artificial intelligence software analyses moving images of a patient\u2019s heart captured during an MRI scan.<\/p>\n It then uses image processing to build a virtual 3D heart, which replicates the way over 30,000 points in the heart contract during a beat.<\/p>\n The researchers fed the system data from hundreds of previous patients. By linking the data with its models, it learnt which attributes of a heart put an individual at a given risk of heart failure.<\/p>\n