Accuracy of Smartphone Camera Applications for Detecting Atrial Fibrillation

Key Points Question What is the overall accuracy of smartphone camera applications that diagnose and screen for atrial fibrillation (AF)? Findings In this meta-analysis of 10 primary diagnostic accuracy studies with 3852 participants, all applications that used photoplethysmography signals to diagnose AF had high sensitivity and specificity. However, the modeled positive predictive value for screening an asymptomatic population aged 65 years and older with a history of hypertension was approximately 20% to 40%, although the negative predictive value was near 100%. Meaning In this study, smartphone camera applications had high sensitivity and specificity for diagnosing AF and appeared adequate for ruling out AF, but their modest positive predictive value suggests that these devices will generate a higher number of false-positive than true-positive results.