Machine learning can predict sudden death in patients with heart failure

Andrea Park - Print  | 

A new study shows that artificial intelligence can be used to predict patients' risk of developing a potentially lethal arrhythmia after experiencing heart failure.

In the study, presented this week at the International Conference on Nuclear Cardiology and Cardiac CT in Lisbon, researchers used a machine learning algorithm to analyze eight variables concerning the health of 529 heart failure patients with known two-year outcomes. After using the data to build a formula, the AI was able to predict with impressive accuracy the chance that a patient would experience sudden arrhythmic events and death within two years of heart failure.

According to researchers, as the algorithm receives further training on more patient data and variables, its predictions could be used to identify both high-risk patients who require implantable ICD or CRT-D devices, as well as those low-risk ones for whom the devices would provide little benefit.

"Optimizing risk evaluation in this way will improve the cost effectiveness of treatment," said Kenichi Nakajima, MD, PhD, study author and clinical professor at Kanazawa University Hospital in Japan.

More articles about AI:
LogitBoost algorithm predicts heart attacks, death with superhuman accuracy
AI can prevent hours of unnecessary testing for stable chest pain
AI retinal scanner that can detect Alzheimer's given FDA 'Breakthrough Device' status

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

To receive the latest hospital and health system business and legal news and analysis from Becker's Hospital Review, sign-up for the free Becker's Hospital Review E-weekly by clicking here.