The Hypertension Notification Feature (HTNF) is a software-only mobile medical application by Apple that uses AI to analyze pulse sensor data collected by Apple Watch to notify users of possible hypertension. It helps adults over 22 years who are not diagnosed with hypertension to identify potential high blood pressure patterns, guiding them for further evaluation, but it is not a diagnostic or monitoring tool. It is designed for over-the-counter use, providing accessible cardiovascular health insights from wearable technology.
The Hypertension Notification Feature (HTNF) is a software-only mobile medical application that analyzes photoplethysmography (PPG) data opportunistically collected by Apple Watch to identify patterns that are suggestive of hypertension and provides a notification to the user. It is intended for over-the-counter use by adults age 22 and over who have not been previously diagnosed with hypertension. It is not intended to replace traditional diagnostic methods, monitor treatment, or serve as blood pressure surveillance. Not for use during pregnancy.
HTNF is a software-only mobile medical application that analyzes PPG data collected opportunistically by Apple Watch. It uses a machine learning model integrated into the Apple Watch to score PPG signals for hypertension risk and an algorithm on iOS devices that aggregates these scores and identifies patterns suggestive of hypertension, which then triggers a notification to the user. The technology involves a deep-learning model trained on large-scale unlabeled data and a linear model for hypertension classification, evaluated on diverse demographic data sets.
Clinical validation included a pivotal study with 2,229 adult subjects without prior hypertension diagnosis wearing Apple Watch and measuring blood pressure with an FDA-cleared home monitor over 30 days. Sensitivity was 41.2% and specificity 92.3% for detecting possible hypertension. Subgroup analyses showed demographic factors did not clinically significantly affect performance. Non-clinical testing included software verification, cybersecurity, human factors validation, and platform impact assessment, all supporting safety and effectiveness.
No predicate devices specified
Submission
2/21/2025
FDA Approval
9/11/2025
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.