London, March 30 Artificial intelligence (AI) can help scientists identify patients at risk of a serious arrhythmia that is capable of triggering cardiac arrest and sudden death.
As part of a new study to be published in European Heart Journal, a network of artificial neurons imitating the human brain was developed by researchers from Inserm, Paris Cite University and the Paris public hospitals group (AP-HP), in collaboration with their colleagues in the US.
During the analysis of data from over 240 000 ambulatory electrocardiograms, this algorithm identified patients at risk of a serious arrhythmia that was capable of triggering cardiac arrest within the following 2 weeks in over 70 per cent of cases.
Each year, sudden cardiac death is responsible for over 5 million deaths worldwide.
AI could help to improve the anticipation of arrhythmias – unexplained heart rhythm disorders which, if severe, can cause fatal cardiac arrest – according to the new study.
As part of this study, a network of artificial neurons was developed by a team of engineers from the company Cardiologs (Philips group) in collaboration with the universities of Paris Cite and Harvard.
What this algorithm does is imitate the functions of the human brain in order to improve the prevention of cardiac sudden death.
The researchers analysed several million hours of heartbeats thanks to data from 240 000 ambulatory electrocardiograms collected in six countries (USA, France, UK, South Africa, India and Czechia).
Thanks to artificial intelligence, the researchers were able to identify new weak signals that herald the risk of arrhythmia. They were particularly interested in the time needed to electrically stimulate and relax the heart ventricles during a complete cycle of cardiac contraction and relaxation.
"
While the artificial neural network is still in the evaluation phase, it showed itself in this study to be capable of detecting at-risk patients in 70 per cent of cases, and no-risk patients in 99.9 per cent of cases.
In the future, this algorithm could be used to monitor at-risk patients in hospital. If its performances are refined, it could also be used in devices such as ambulatory Holters that measure blood pressure to reveal hypertension risks. It could even be used in smartwatches.
The researchers now aim to conduct prospective clinical studies to test the efficacy of this model under real-world conditions.
Disclaimer: This post has been auto-published from an agency feed without any modifications to the text and has not been reviewed by an editor