Atrial fibrillation (AFib) affects about 59 million people globally and is the most common type of cardiac arrhythmia. While AFib itself is not usually life threatening, it can increase the risk of mortality from cardiovascular conditions such as stroke, heart attack, and heart failure. Early detection of AFib is crucial for better health outcomes, as it can also lead to other diseases such as dementia and gastrointestinal disorders. Researchers at the University of Luxembourg have developed new technology to predict cardiac arrhythmia about 30 minutes before it occurs by using artificial intelligence and electrocardiogram information gathered through wearable devices. This study was recently published in the journal Patterns.
The AI model developed by the researchers, called WARN (Warning of Atrial fibRillatioN), inputs short segments of 30 seconds of heart rate and outputs the probability of an imminent switch to AFib. The model was trained and tested on 24-hour recordings of electrocardiogram data gathered through Holter devices worn by 350 individuals. The researchers found that the WARN model was able to predict the transition from normal cardiac rhythm to atrial fibrillation with an average warning of 30 minutes before onset with about 80% accuracy. This early warning could allow patients to take preventive measures such as anti-arrhythmia and anticoagulant medication at an early time point.
While the study collected heart electrical activity data via a medical device, the researchers believe that the same model could one day be used through everyday smartwatches. This could allow for continuous monitoring of the cardiovascular system and early detection of subtle changes in its dynamics. The researchers plan to personalize the algorithm to individuals in the future by having patients wear a smartwatch for an extended period of time to learn the specific features of the disease for that individual. With further development, this technology could help patients with AFib be more proactive in treating their condition.
Dr. Paul Drury, a board-certified cardiologist and associate medical director of electrophysiology, commented on the study, noting that the ability to predict AFib episodes before they occur could significantly improve treatment outcomes. He emphasized the importance of detecting AFib early to allow patients to treat the condition before it starts. While smart devices are currently good at detecting AFib, they cannot predict the condition. Implementing AI technology into wearable devices could help patients with AFib be more proactive in managing their condition by detecting triggers and proactively treating impending episodes.
Moving forward, the researchers plan to write apps for different smartwatches and test them in prospective studies to further validate their findings. This technology has the potential to revolutionize the way AFib is detected and managed, ultimately leading to better health outcomes for patients with this condition. By leveraging artificial intelligence and wearable technology, this study represents a significant step forward in predicting and preventing cardiac arrhythmia in a timely manner.