Researchers have developed an AI-based tool capable of predicting episodes of mood disorders, including bipolar disorder, by analyzing sleep-wake patterns recorded by wearable devices like smartwatches.

The tool uses data collected from users’ daily sleep cycles to detect disturbances that may signal a potential mood episode. People with mood disorders often experience periods of intense emotions—whether depression, sadness, joy, or mania—that are linked to disrupted sleep rhythms.

The research team, including experts from the Institute for Basic Science in South Korea, highlighted that the increasing use of wearable devices has made it easier to collect data that can help monitor and predict health conditions like mood disorders.

This breakthrough could help people at risk of such episodes receive early intervention, ultimately improving mental health care.