A team of researchers has created a cutting-edge AI model capable of forecasting irregular heartbeats, known as cardiac arrhythmias, approximately half an hour before they occur.
Their study revealed that the model demonstrated an impressive 80 percent accuracy rate in anticipating the shift from a regular heart rhythm to atrial fibrillation, the prevalent form of cardiac arrhythmia characterized by erratic beating of the heart’s upper chambers.
The research team, which includes scientists from the University of Luxembourg, highlighted that their AI model, designed to provide early alerts, could be seamlessly integrated into smartphones for analyzing data collected by smartwatches.
According to them, these alerts could empower individuals to proactively manage their cardiac rhythm and take preventive actions to maintain stability. The findings of their study are detailed in the journal Patterns.
To develop the model, the team utilized 24-hour recordings obtained from 350 patients at Tongji Hospital in Wuhan, China. Named WARN (Warning of Atrial fibRillatioN), the model relies on deep-learning, a form of machine-learning AI algorithms capable of discerning patterns from historical data to make predictions.
READ MORE
Global Experts Advocate Standardization Of MGB/OAGB Surgery
Deep-learning stands out for its specialization due to its multi-layered decision-making process.
The researchers discovered that WARN issued early warnings, typically 30 minutes before the onset of atrial fibrillation, making it the inaugural method to offer alerts significantly ahead of time, they noted.
“We used heart rate data to train a deep learning model that can recognise different phases — (normal) sinus rhythm, pre-atrial fibrillation and atrial fibrillation — and calculate a ‘probability of danger’ that the patient will have an imminent episode,” Jorge Goncalves, from the Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, and the study’s corresponding author, said.
Goncalves mentioned that as atrial fibrillation approaches, there’s a gradual rise in probability until it surpasses a predefined threshold, triggering an early warning.
The researchers highlighted the AI model’s low computational cost, making it “perfect for incorporation into wearable technologies.”
“These devices can be used by patients on a daily basis, so our results open possibilities for the development of real-time monitoring and early warnings from comfortable wearable devices,” study author Arthur Montanari, an LCSB researcher, said.
ALSO READ
NewsX A-List: Prasada Rao Daggumalla on Economic Discipline and Financial Due Dilligence
