Heart Rhythm Society
HRS 2025: AI predicts hospitalizations with 91% accuracy using Fitbit data
A recent study presented at Heart Rhythm 2025 demonstrated that AI can predict hospitalization risks with 91% accuracy using data from wearable fitness trackers like Fitbits. Researchers analyzed heart rate and step count data from over 14,000 participants, 70% of whom were women, as part of NIH’s All of Us Research Program. The study highlights the potential of AI and wearable devices in providing continuous, detailed health monitoring, which can significantly enhance patient care by enabling clinicians to better risk-stratify patients. The approach could also revolutionize the management of chronic conditions and improve clinical outcomes by leveraging the vast datasets generated by wearable technology.
Sources:
(2025, April 25). Heart Rhythm Society. AI Shown to Help Predict Hospitalization Risks Using Fitbit Data Analyzing Heart Rate and Step Count. [News release]. https://www.hrsonline.org/news/ai-shown-to-help-predict-hospitalization-risks-using-fitbit-data/
Predicting Patient Risk and Outcomes Using Artificial Intelligence: Predicting All-Cause Hospitalizations Using Machine Learning Applied to Wearable Fitness Tracker Step Data. Presented at Heart Rhythm Society 2025. https://www.heartrhythmjournal.com/article/S1547-5271(25)00240-1/pdf