London: Scientists have developed an artificial intelligence (AI) algorithm capable of identifying patients at risk of severe arrhythmia, a condition that can lead to cardiac arrest and sudden death.
The study, soon to be published in the European Heart Journal, involved researchers from Inserm, Paris Cité University, and the Paris public hospitals group (AP-HP), in collaboration with their US counterparts.
Also Read
Analysing data from over 240,000 ambulatory electrocardiograms, the AI model accurately predicted a serious arrhythmia that could lead to cardiac arrest within two weeks in more than 70% of cases.
Sudden cardiac death claims over five million lives globally each year. The study suggests AI could enhance early detection of arrhythmias—irregular heart rhythms that, if left untreated, may result in fatal cardiac events.
The research team, including engineers from Cardiologs (Philips Group) and experts from Paris Cité and Harvard University, developed an artificial neural network that mimics brain functions to improve the prevention of sudden cardiac death.
By examining millions of hours of heartbeat data from six countries—USA, France, UK, South Africa, India, and Czechia—the AI algorithm identified weak signals indicating the risk of arrhythmia. Researchers focused on the electrical stimulation and relaxation times of the heart’s ventricles during a full contraction and relaxation cycle.
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.
"By analysing their electrical signal for 24 hours, we realised that we could identify the subjects susceptible of developing a serious heart arrhythmia within the next two weeks. If left untreated, this type of arrhythmia can progress towards a fatal cardiac arrest", explained Dr Laurent Fiorina, researcher at the Paris Cardiovascular Research Centre (PARCC) (Inserm/Paris Cite University).
While still in the evaluation phase, the neural network demonstrated its ability to identify at-risk patients in 70% of cases and confirm no-risk cases with 99.9% accuracy.
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.
IANS
Published: 30 Mar 2025, 10:42 am IST
Related Topics
Disclaimer: Kindly avoid objectionable, derogatory, unlawful and lewd comments, while responding to reports. Such comments are punishable under cyber laws. Please keep away from personal attacks. The opinions expressed here are the personal opinions of readers and not that of Mathrubhumi.