Accuracy of Smartphone Camera Applications for Detecting Atrial Fibrillation

Abstract

IMPORTANCE Atrial fibrillation (AF) affects more than 6 million people in the United States; however, much AF remains undiagnosed. Given that more than 265 million people in the United States own smartphones (>80% of the population), smartphone applications have been proposed for detecting AF, but the accuracy of these applications remains unclear. OBJECTIVE To determine the accuracy of smartphone camera applications that diagnose AF. DATA SOURCES AND STUDY SELECTION MEDLINE and Embase were searched until January 2019 for studies that assessed the accuracy of any smartphone applications that use the smartphone's camera to measure the amplitude and frequency of the user's fingertip pulse to diagnose AF. DATA EXTRACTION AND SYNTHESIS Bivariate random-effects meta-analyses were constructed to synthesize data. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) of Diagnostic Test Accuracy Studies reporting guideline. MAIN OUTCOMES AND MEASURES Sensitivity and specificity were measured with bivariate random-effects meta-analysis. To simulate the use of these applications as a screening tool, the positive predictive value (PPV) and negative predictive value (NPV) for different population groups (ie, age Ն65 years and age Ն65 years with hypertension) were modeled. Lastly, the association of methodological limitations with outcomes were analyzed with sensitivity analyses and metaregressions. RESULTS A total of 10 primary diagnostic accuracy studies, with 3852 participants and 4 applications, were included. The oldest studies were published in 2016 (2 studies [20.0%]), while most studies (4 [40.0%]) were published in 2018. The applications analyzed the pulsewave signal for a mean (range) of 2 (1-5) minutes. The meta-analyzed sensitivity and specificity for all applications combined were 94.2% (95% CI, 92.2%-95.7%) and 95.8% (95% CI, 92.4%-97.7%), respectively. The PPV for smartphone camera applications detecting AF in an asymptomatic population aged 65 years and older was between 19.3% (95% CI, 19.2%-19.4%) and 37.5% (95% CI, 37.4%-37.6%), and the NPV was between 99.8% (95% CI, 99.83%-99.84%) and 99.9% (95% CI, 99.94%-99.95%). The PPV and NPV increased for individuals aged 65 years and older with hypertension (PPV, 20.5% [95% CI, 20.4%-20.6%] to 39.2% [95% CI, 39.1%-39.3%]; NPV, 99.8% [95% CI, 99.8%-99.8%] to 99.9% [95% CI, 99.9%-99.9%]). There were methodological limitations in a number of studies that did not appear to be associated with diagnostic performance, but this could not be definitively excluded given the sparsity of the data. CONCLUSIONS AND RELEVANCE In this study, all smartphone camera applications had relatively high sensitivity and specificity. The modeled NPV was high for all analyses, but the PPV was modest, (continued) 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 app...

Psychological aspects of atrial fibrillation: A systematic narrative review

“…The true proportion of silent AF in the general population is currently unknown, because AF screening even at repeated time points remains a random snapshot, unable to capture the wide range of paroxysmal AF episodes within an individual over time [ 50 ]. However, smartphone applications and other technological solutions (e.g., ECG Telecard) are currently under evaluation [ 51 ] in efforts to more accurately assess the true incidence AF despite the disease’s episodic nature and its propensity to remain asymptomatic. Silent and clinically apparent episodes may occur in parallel: in patients with paroxysmal AF, asymptomatic arrhythmia events occur even significantly more frequently than symptomatic arrhythmia events.…”

Implementation of an on-demand app-based heart rate and rhythm monitoring infrastructure for the management of atrial fibrillation through teleconsultation: TeleCheck-AF

“…The on-demand mHealth application for a limited predefined time period of 7 days prior the scheduled teleconsultation within the TeleCheck-AF approach is novel and differs from previous settings where mHealth is typically used for a longer rhythm monitoring period or provide decision support, risk assessment and patient education according to existing guidelines. 7 , 17 , 18 The goal in TeleCheck-AF is to make heart rate and rhythm information available, to allow a better assessment of the disease state of the patient and to support in treatment decisions through teleconsultation. The limited validity, regulated by a QR code, avoids unnecessary data-load.…”

“…This app is CE marked, connected to a secured and certified cloud and validated (sensitivity: 96%; specificity: 97%) to detect AF via PPG signals and to provide rate measures during sinus rhythm and AF. 6 , 7 Patients are instructed to use this app three times every day and in case of symptoms to provide a semi-continuous longitudinal information about heart rate, rhythm and symptoms. The simultaneous assessment of heart rhythm and symptoms in the app allows assessment of symptom-rhythm correlation.…”

On‐demand mobile health infrastructures to allow comprehensive remote atrial fibrillation and risk factor management through teleconsultation

“…As most PPG algorithms are developed for AF screening scenarios, they operate in a high sensitivity mode, resulting in a higher number of false positive recordings. [7] Therefore, in the setting of AF screening, PPG-detected episodes suggestive of AF need to be confirmed by an ECG. Despite crucial differences between PPG and ECG F I G U R E 1 Remote heart rate and rhythm monitoring: (semi-) continuous longitudinal vs ondemand F I G U R E 2 Different mobile health devices technologies for heart rhythm monitoring, most of the PPG-based algorithms are validated to detect AF with a high sensitivity and specificity.…”

“…Despite crucial differences between PPG and ECG F I G U R E 1 Remote heart rate and rhythm monitoring: (semi-) continuous longitudinal vs ondemand F I G U R E 2 Different mobile health devices technologies for heart rhythm monitoring, most of the PPG-based algorithms are validated to detect AF with a high sensitivity and specificity. [7] Additionally, there is already some data that PPG technology is nearly as accurate as ECG to detect AF. [8,9] In the validation studies for these devices, atrial high rate episodes (AHRE) from CIEDs have not been taken into account.…”