Actively Recruiting
Validating Machine-Learning Algorithms to Detect Atrial Fibrillation Using Wearable Devices in Post-Stroke Patients
Led by Emory University · Updated on 2026-01-21
500
Participants Needed
1
Research Sites
52 weeks
Total Duration
AI-Summary
What This Trial Is About
Atrial Fibrillation AF is an abnormal heart rhythm that often goes undiagnosed because it usually has no symptoms in early stages. This research aims to validate a new machine-learning software that detects abnormal heart rhythms using data from consumer smart devices like Apple or Fitbit. The study focuses on patients who have had a stroke of uncertain cause and are being followed at a stroke center. Participants will wear standard cardiac monitoring devices approved by the FDA, such as ambulatory ECG patches or implantable recorders, alongside a consumer wrist device like a MOTO 360 smartwatch or Samsung Galaxy Watch 6. They will wear the study device for 30 days, about 23 hours a day, at home. The data collected will be uploaded and analyzed using the investigational software to compare its ability to detect AF with the standard monitoring methods. During the study, participants heart rhythms will be continuously monitored with both the standard devices and the wearable consumer devices. Researchers will assess the quality of the data, including the effects of wrist motion and skin tone on readings. The main measures are how well the software detects AF and predicts its occurrence compared to electronic health records. The study may last up to five years, with evaluations done at the end of the monitoring period and beyond.
CONDITIONS
Brief Title
DELTA (Detecting and Predicting Atrial Fibrillation in Post-Stroke Patients)
Research Team
X
Xiao Hu, PhD
C
Corey Williams
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here