New Data Suggest Apple Watch Algorithm is Accurate in Atrial Fibrillation Detection

_{©Andrey Popov/AdobeStock}

An Apple Watch feature designed to detect atrial fibrillation (AF) was associated with a low rate of false-positive detections and high specificity, but only modest sensitivity for detections in persons with a history of AF, according to a new study published in the Journal of Cardiovascular Electrophysiology.

The Apple Watch Irregular Rhythm Notification (IRN) feature uses photoplethysmography to identify prolonged episodes of irregular rhythm suggestive of AF. The US Food and Drug Administration cleared the technology for adults with no previous history of AF; however, these devices are increasingly being used for AF management, according to researchers.

“Episodes of AF can be asymptomatic, and therefore modalities for continuous monitoring may be used to quantify the occurrence of AF over a prolonged timeframe,” wrote first author Jeremiah Wasserlauf, MD, MS, and colleagues. “The objective of the present study was to determine the accuracy of the IRN for AF detection in subjects with a previous diagnosis of non-permanent AF.”

Wasserlauf and colleagues examined data from 30 adults from 3 hospital systems who had a history of nonpermanent AF and either an insertable cardiac monitor (ICM) or cardiac implanted electronic device (CIED) with <5% ventricular pacing. Participants were fitted with an Apple Watch Series 5 and asked to wear the watch during waking hours for a minimum of 14 hours per day for 6 months. The mean age of participants was 65 years and 40% were women. Among the cohort, 10 persons had ICMs and 20 had CIEDs.

Investigators compared AF episodes between the ICM/CIED and IRN feature.

“Participants provided screen shots of all IRNs received during the study period and these episodes were compared to downloads from the patient’s ICMs/CIEDs,” wrote the research team. “AF events detected by ICM/CIED without an associated IRN were further investigated by a screenshot of the participant’s ‘Activity’ page for the corresponding day. If the participant’s ‘Move’ bar graph was at zero during the time that the ICM/CIED detected an event, the participant was deemed to not be wearing their AW [Apple Watch] during this time.”

The primary endpoints were sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the IRN by subject for AF ≥1 hour. Secondary endpoints were sensitivity and PPV by AF episode ≥1 hour. Analysis was limited to a maximum of 10 ICM/CIED episodes per participant and included only AF episodes that occurred during active Apple Watch use confirmed by activity data.

Findings

Among the cohort, 11 had AF on ICM/CIED while wearing an Apple Watch, of whom 8 were detected by IRN. There were no false-positive IRN detections by participants (72% sensitivity, 100% specificity, 100% PPV, and 90% NPV), according to investigators. Five participants had AF only when the Apple Watch was not worn.

There were 70 AF episodes observed on ICM/CIED, 35 of which occurred while the subject was wearing an Apple Watch. Of these, 21 were detected by IRN with 1 false positive. Therefore, according to researchers, the secondary endpoints of accuracy “by episode” during watch wear time were a sensitivity of 60% and a PPV of 95.5% for AF episodes lasting ≥1 hour.

The sensitivity for AF episodes lasting 1-12 hours and > 12 hours was 58% and 75%, respectively (P=.635).

“The current IRN algorithm appears accurate for AF screening as currently indicated, but increased sensitivity and wear times may be necessary for disease management,” concluded Wasserlauf et al.

Reference: Wasserlauf J, Vogel K, Whisler C, et al. Accuracy of the Apple Watch for detection of AF: A multi-center experience. J Cardiovasc Electrophysiol. Published online March 21, 2023. doi:10.1111/jce.15892.