Garmin data used to predict panic attacks with over 90% accuracy in study

Predicting Panic Attacks with Garmin Data

Researchers at the National Taiwan University have published studies showing that physiological data from Garmin trackers can be used to predict panic attacks with 92% accuracy.

The studies, which took place over several years, used biometric insights from the Garmin Vivosport series to collect data on metrics like heart rate, sleep, and activity levels.

This data was combined with self-reported information on emotional state and environmental data from a mobile app, and then fed into a machine learning model to predict the likelihood of a participant having a panic attack.

The research went beyond just prediction, with surprisingly high accuracy of 92%.

Author's summary: Garmin data predicts panic attacks with 92% accuracy.

more

Wareable Wareable — 2025-10-16

More News