Abstract 55: Detection of Atrial Fibrillation Using a Smartphone Camera
Introduction: Atrial fibrillation (AF) is the most common sustained dysrhythmia in the U.S. and is associated with significant morbidity and mortality. Although new AF treatment strategies have emerged over the last decade, a major challenge facing clinicians and researchers is the paroxysmal, often short-lived, and sometimes asymptomatic nature of AF. We hypothesized that a smartphone can detect AF based on its ability to record heart beat variability by placing a fingertip on the built-in camera.
Methods: In this prospective clinical investigation, we recruited 33 participants at a tertiary care medical center who presented with persistent AF prior to elective cardioversion. We recorded 2-5 minutes of pulse readings from participants’ index finger using an iPhone 4S before (AF cases), and after, electrical cardioversion (Sinus rhythm controls). With heart beat interval time series obtained from changes in color signals of a fingertip recording, we compared the results of an AF detection algorithm using Root Mean Square of Successive Difference in combination with Shannon Entropy and Sample Entropy in comparison to the gold-standard of an electrocardiogram.
Results: The AF detection accuracy was 97.67% (sensitivity of 96.08% and specificity of 99.97%) for each sample when a combination of the three signal processing techniques were applied compared to the gold-standard electrocardiographic recordings. All of the 33 AF episodes were detected. In addition, we tested on 29 healthy subjects and found that the accuracy (specificity) was 99.51%.
Conclusions: In this paper, we show that a smartphone can accurately detect AF based on its ability to obtain RR time series. More accessible methods to accurately detect AF are necessary, and the use of existing smartphone technologies has potentially revolutionary clinical applications for in-home monitoring for AF.
- © 2012 by American Heart Association, Inc.