Sleep and circadian rhythm data could be used to predict mood episodes in people who have mood disorders.

The study analysed 429 days of data from 168 mood disorder patients. Data were collected from wearable devices, such as smartwatches.
Researchers then extracted 36 sleep and circadian rhythm features. When applied to machine learning algorithms, these features were used to achieve highly accurate predictions for depressive, manic and hypomanic episodes.
The study found that daily changes in circadian rhythm were a key predictor of mood episodes. Delayed circadian rhythms increased the risk of depressive episodes, while advanced circadian rhythms increased the risk of manic episodes.
‘This study demonstrates the potential of using only sleep-wake data from wearable devices to predict mood episodes, increasing the feasibility of real-world applications,’ said lead researcher Professor Heon Jeong Lee. ‘We envision a future where mood disorder patients can receive personalised sleep pattern recommendations through a smartphone app to prevent mood episodes.’
Image | Unsplash