Researchers have discovered a revolutionary new AI model that can predict cardiac arrhythmia i.e. irregular heartbeat approximately 30 minutes in advance!!
This model has demonstrated 80% accuracy in predicting the transition from a normal cardiac rhythm to atrial fibrillation, the most common type of cardiac arrhythmia in which the heart's upper chambers (atria) beat irregularly and are out of sync with the lower ones (ventricles). A team, including researchers at the University of Luxembourg, developed this model. They've stated that WARN (Warning of Atrial fibRillatioN), the AI model offers early warnings and can integrate the data from smartwatches to smartphones with one easy installation. This study has been published in the Journal Patterns. Because of its early prediction, it gives patients time to stabilize their heartbeat and take necessary precautions.
The research team trained the AI model on 24-hour recordings obtained from 350 patients at Tongji Hospital in Wuhan, China, during the development phase. WARN is based on deep learning, a type of Machine Learning (ML) AI algorithm that predicts irregular heartbeat based on the patterns from previous data. Since it has multiple layers in the decision-making process, ML is more specialized.
The team added that WARN gives a prediction at least 30 minutes before any sign of atrial fibrillation and is the first method to foresee this far before onset.
Jorge Goncalves, from the Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, and the study’s corresponding author, said that they used heart rate data that can differentiate phases like (normal) sinus rhythm, pre-atrial fibrillation, and atrial fibrillation to train a deep learning model and calculate the 'probability of danger' as in how likely it is that the patient will face a problem. If a patient is about to approach atrial fibrillation, the probability increases and the AI model gives an early warning.
The researchers have added that since this computational technique is affordable and cost-effective, it's a great model to integrate into wearable technologies.
As these devices can be used by patients daily, the results open more possibilities for developing real-time monitoring and early warnings from convenient wearable devices said study author Arthur Montanari, an LCSB researcher.
(Input from various sources)
(Rehash/Aditi Madathingal/MSM)
