Sleep trackers may spot depression relapse weeks before symptoms return, a study of 93 adults with remitted major depressive disorder suggests.
Researchers followed people whose symptoms had eased but who remained at risk of recurrence.
Participants wore research-grade wrist actigraphy devices, which track movement to estimate sleep and activity, for up to two years, generating nearly 32,000 days of data.
The study found that increasingly irregular sleep patterns nearly doubled the risk of relapse.
The strongest predictor was a dampened circadian rhythm, where the contrast between daytime activity and night-time rest became less distinct.
In the weeks leading up to recurrence, sleep-wake schedules grew progressively more erratic, while individuals who stayed in remission showed far more stable daily rhythms.
The research was conducted across five sites through the Canadian Biomarker Integration Network in Depression, led by Benicio Frey at McMaster University in Hamilton, Ontario, Canada.
Frey said: “Our findings are consistent with prior research showing that sleep disturbance functions both as a symptom of an acute depressive episode and as an early warning signal of future relapse.
“The data suggest that the biology may extend beyond sleep itself, pointing to broader disruptions in circadian rhythms.”
Frey said early changes in daily rhythms could create a window for action, allowing patients and clinicians to reinforce sleep hygiene, adjust routines or seek follow-up before symptoms fully return.
Benjamin W. Nelson, senior clinical research scientist in digital biomarkers at Verily Life Sciences and adjunct professor at Harvard Medical School, said the study advances digital monitoring by pairing continuous, long-term actigraphy with structured clinician assessments every two months, and by using formal diagnostic criteria rather than self-reported questionnaires alone.
However, Nelson cautioned that the modest sample size and relatively homogeneous population may limit how broadly the findings apply. The study also relied only on actigraphy, without additional sensors that could provide more detailed sleep data.
If replicated, he said, wearable-derived sleep and activity metrics could eventually support relapse monitoring, particularly for people with recurrent depression.
