JMIR Publications

ABSTRACT

Background:

Atrial fibrillation (AF) affects over 33 million people globally, with many cases remaining undiagnosed due to the paroxysmal nature of the condition. Current portable AF detection devices require additional hardware, and their cost may limit their accessibility in community screening programs.

Objective:

To assess the technical feasibility of a novel smartphone camera-based AF detection system through comparison with a portable ECG device under real-world home monitoring conditions.

Methods:

We conducted a single-patient pilot feasibility study over 12 consecutive days. Simultaneous 60-second recordings were carried out three times daily using the electronRx smartphone application and a Kardia portable ECG device. The primary outcome was device agreement in rhythm classification between the two systems.

Results:

Twenty-four paired recordings were obtained. Device agreement was achieved in 21 of 23 recordings (91.7%). The smartphone system detected 4 out of 5 episodes classified as AF by the Kardia device, and agreed with 17 of 18 recordings classified as normal sinus rhythm. Two discordant cases were identified: one false negative associated with atrial flutter presenting as a fixed 3:1 atrioventricular block, and one false positive related to poor signal quality due to suboptimal lighting conditions. Signal quality was found to significantly affect performance, with 100% agreement in recordings of good quality versus 75% in recordings of poor quality.

Conclusions:

This pilot study demonstrates the technical feasibility of smartphone camera-based rhythm analysis for AF detection. The approach shows promise as an accessible screening tool, although the single-patient design and identified technical limitations necessitate larger validation studies before any clinical application can be considered.