The Atrial Fibrillation History Feature is a software application designed to analyze pulse rate data from Apple Watch sensors to detect episodes of irregular heart rhythm indicative of atrial fibrillation (AFib). It provides users with estimates of the amount of time spent in AFib over past periods and visualizes this alongside lifestyle data to help users understand the impact of their behavior on their condition. It assists patients in monitoring AFib burden over time but is not meant to replace traditional diagnosis or treatment methods.
An over-the-counter software-only mobile medical application intended for users 22 years and older diagnosed with atrial fibrillation (AFib) that analyzes pulse rate data to identify irregular heart rhythms and estimate AFib burden.
The device uses photoplethysmography (PPG) sensor data collected by Apple Watch sensors to detect irregular heart rhythms consistent with AFib. It employs machine learning techniques, specifically a convolutional neural network, trained on extensive pulse data to classify rhythms and estimate AFib burden over specified time windows. The software is implemented as mobile apps on Apple Watch and iPhone, integrating with the Apple Health app to visualize data.
Performance validation included clinical and internal design control testing. The AFib History Feature's rhythm classification algorithm achieved 97% sensitivity and 99.0% specificity in development data and showed 92.6% sensitivity and 98.8% specificity in clinical validation with 413 participants. The feature accurately estimated AFib burden compared to ECG references, with most estimates within ±10% of reference values. Human factors testing confirmed safety and usability.
No predicate devices specified
Submission
12/20/2021
FDA Approval
6/3/2022
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.