Smartphone cameras could play an important role in the diagnosis of AFib, according to new findings published in JAMA Network Open. Researchers warned, however, that using camera-based applications for such a purpose leads to a sharp rise in false-positive results.
The authors explored 10 studies focused on smartphone applications that measure the amplitude and frequency of the user’s fingertip pulse to diagnose AFib. The studies occurred in 2016-2018 and included data from more than 3,800 users.
Overall, the applications had a combined sensitivity of 94.2% and specificity of 95.8%. The positive predictive value (PPV) for detecting AFib in asymptomatic patients 65 years old and older was between 19.3% and 37.5%. The negative predictive value (NPV) for that same patient cohort, however, was between 99.8% and 99.9%. When patients had hypertension, both the PPV and NPV did improve.
The researchers did note that these camera-based applications “seem to be able to rule out AFib in a healthy, asymptomatic patient,” but also pointed to the technology’s shortcomings.
“Regarding AFib screening, if any of these applications reach a diagnosis of sinus rhythm in a healthy, asymptomatic person, it is likely this person does not have AFib,” wrote lead author Jack W. O’Sullivan, MMBS, DPhil, Stanford University School of Medicine, and colleagues. “Conversely, we cannot draw the same conclusion from a positive result. In fact, our model suggests that if these applications detect AFib in an asymptomatic person, the result is most likely to be a false-positive.”
O’Sullivan et al. concluded that further research in this area is needed, including investigations into how these camera-based applications may work with “other high-risk population groups” and whether or not they can monitor chronic AFib.
Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.