Review of evidence on artificial intelligence in cardiac imaging
CardioTeca reviews what has been measured with randomized or prospective studies on artificial intelligence programs in cardiac imaging and what is under investigation. The studied programs measure LVEF, strain, volumes and wall thickness, segment MRI chambers, score coronary calcium, calculate CT-derived FFR and guide the probe for beginners. In the randomized studies, a physician or technician later reviewed the program's output.
In 40 seconds
- A deep learning algorithm calculated LVEF with a mean absolute error of 4.1% at its center and 6.0% in another healthcare system.
- In a randomized, blinded study, the cardiologist changed the initial LVEF by more than 5 points in 16.8% of cases with the program versus 27.2% with the technician.
- The PROTEUS study did not reach its prespecified non-inferiority margin for appropriate referral to coronary angiography.
IASummary generated by artificial intelligence from a story by CardioTeca. It may contain errors: the original source prevails.





Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.