Computer Scientists at Imperial College London in collaboration with clinicians at the MRC London Institute of Medical Sciences (LMS) have developed AI software that creates a beating 3D replica of a patient’s heart that doctors can use to assess their heart health.

The software works by analysing MRI images of the patient’s moving heart along with information from blood tests and other medical data.

In a recent study published in the journal Radiology the scientists used the software to predict survival in patients with pulmonary hypertension better and more quickly than current methods, which involve measurements of heart function by hand.

Using data from 250 patient the software analysed moving MRI images of each patient’s heart to replicate the way over 30,000 points in the heart contract during each beat. Using this information the software created a ‘virtual 3D heart’ of each patient and automatically learned which features were associated with early death or heart failure.

“This is the first time computers have interpreted heart scans to accurately predict how long patients will live. It could transform the way doctors treat heart patients,” said Lead Author from the LMS, Dr Declan O’Regan.

The scientists are confident that this software could play an important role in the future treatment of patients with different types of heart disease.

“The computer performs the analysis in seconds and simultaneously interprets data from imaging, blood tests and other investigations without any human intervention. It could help doctors to give the right treatments to the right patients, at the right time,” said Co-author, Dr Tim Dawes, who’s also from LMS and developed the algorithms for the software.

There are plans underway to test the software using patient data from a different hospital to the one in which it was developed, to verify the findings. The end goal is to develop software to make predictions not only about survival, but also about which type of treatment will work best for different patients.

For more information contact, like us on Facebook or tweet us @eHealthNewsZA.