AI-Enabled Clinical Alerts Boost Heart Valve Treatment Rates in Multicenter Trial
AI-powered clinical alerts improved heart valve disease treatment rates by 40% in a multicenter trial involving 35 hospitals. The system increased timely interventions and reduced disparities in care access across different patient populations.
Electronic clinician notifications powered by artificial intelligence significantly improve the timely evaluation and treatment of patients with heart valve disease, according to new data from a multicenter trial. The ALERT Trial demonstrated that AI-enabled alerts were 27% more effective at notifying clinicians about patient cardiovascular status than usual care, leading to a 40% relative increase in valve interventions and a 27% increase in multidisciplinary heart team evaluations within 90 days.
The study, which involved 765 clinicians ordering 2,016 echocardiograms across 5 U.S. health systems encompassing 35 hospitals, met its primary endpoint defined as time to surgical or transcatheter valve intervention followed by time to multidisciplinary heart team clinic visit within 90 days after the index echocardiogram. The findings revealed that electronic clinician notifications achieved a win ratio of 1.27 compared to usual care.
Data from the trial suggest white patients represent the majority (90%) of all transcatheter aortic valve replacement procedures, while patients who are Black, Hispanic, Asian, or part of other racial groups are not being treated with TAVR at the same rates as white patients. Additionally, women with aortic stenosis continue to experience meaningful disparities in care, as they are less likely to be referred for timely evaluation and valve intervention compared to men.
The study utilized an AI-enabled care pathway platform that automatically identifies significant aortic stenosis or mitral regurgitation patients who may meet guideline-indicated therapy criteria but do not have a treatment plan in place. Symptomatic severe aortic stenosis is a common, yet severe form of heart valve disease that impacts approximately 250,000 people annually in the United States and remains undertreated according to AHA/ACC Guidelines criteria.
Untreated symptomatic severe aortic stenosis carries a high risk of mortality within two years, yet significant undertreatment persists particularly among patients from racial and ethnic minority groups and those with certain hemodynamic profiles. The research highlights the value of real-time clinical alerts to accelerate diagnosis and specialist referral, helping ensure that more patients—regardless of race, ethnicity, geography, hemodynamics, or other factors—have access to guideline-directed, life-saving care.
Findings from the study were presented at the American College of Cardiology Annual Scientific Sessions in New Orleans and simultaneously published in the Journal of the American College of Cardiology.