Mayo Clinic Study Shows AI Can Help Detect Atrial Fibrillation
Mayo Clinic researchers found that an artificial intelligence-based screening strategy that uses electrocardiogram data could determine patient risk for a stroke.
Source: Getty Images
By - Aiming to lower the prevalence of undiagnosed atrial fibrillation and stroke, researchers from Mayo Clinic tested an artificial intelligence (AI)-based screening strategy designed to determine new cases of atrial fibrillation following an evaluation of electrocardiograms (ECGs).
Atrial fibrillation is an irregular heartbeat that can result in blood clots, potentially causing a stroke. To enhance the detection of atrial fibrillation, researchers from Mayo Clinic evaluated a strategy guided by an AI algorithm previously developed by nference and Mayo Clinic and licensed to Anumana Inc., a health technology company. The algorithm is designed to identify atrial fibrillation in normal sinus rhythm from an ECG.
"We believe that atrial fibrillation screening has great potential, but currently the yield is too low and the cost is too high to make widespread screening a reality," said Peter Noseworthy, MD, a cardiac electrophysiologist at Mayo Clinic and lead author of the study, in the press release. "This study demonstrates that an AI-ECG algorithm can help target screening to patients who are most likely to benefit."
The study included 1,003 patients who participated in continuous monitoring and 1,003 who received usual care. Among those in the intervention group, the algorithm detected atrial fibrillation in six of 370 low-risk patients and 48 of 633 high-risk patients.
Thus, researchers determined that the AI-guided screening led to increased detection of atrial fibrillation. ECGs are used in many different circumstances; however, using AI-guided ECGs to diagnose atrial fibrillation has several benefits, according to the press release. For instance, the likelihood of a 10-second ECG recognizing abnormal patterns is unlikely. The AI-supported strategy can help identify high-risk patients even if they display normal rhythms on their ECG, the press release states.
"The study shows that an AI algorithm can select a subgroup of older adults who might benefit more from intensive monitoring. If this new strategy is broadly implemented, it could reduce undiagnosed atrial fibrillation, and prevent stroke and death in millions of patients across the globe," said senior study author Xiaoxi Yao, PhD, a health outcomes researcher in the Department of Cardiovascular Medicine and the Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, in the press release.
Researchers intend to conduct a multicenter hybrid trial to determine the applicability of AI-ECG workflows across diverse clinical settings and patient populations.
Recently, AI has been increasingly used to enhance diagnosis practices.
A study from May described a deep-learning model that detected retinal abnormalities with ocular fundus images. The model could help enhance the early diagnosis of retinal diseases in underdeveloped areas.
In April, researchers from the RIKEN Center for Advanced Intelligence Project noted that using AI in ultrasound procedures led to higher accuracy in diagnosing heart diseases.
.
