new-ai-tool-predicts-mood-disorders-from-sleep-wake-data

Scientists have created a tool powered by AI that can forecast episodes of mood disorders in individuals by utilising only sleep-wake data obtained from wearable devices like smartwatches.

 

Individuals dealing with mood disorders, such as bipolar disorder, undergo extended periods of feelings ranging from sadness and depression to joy or mania. There is a close relationship between mood disorders and sleep-wake patterns, where disturbances may trigger a mood episode.

 

The research team, which includes members from the Institute for Basic Science in South Korea, noted that the increasing prevalence of wearable devices has facilitated the easier collection of health-related data.

 

"By developing a model that predicts mood episodes based solely on sleep-wake pattern data, we have reduced the cost of data collection and significantly improved clinical applicability.

 

"This study offers new possibilities for cost-effective diagnosis and treatment of mood disorder patients," lead researcher Kim Jae Kyoung said.

 

For the study, published in the journal 'NPJ Digital Medicine', the researchers analysed 429 days' worth of data from 168 mood disorder patients. Thirty-six sleep-wake, or circadian, rhythms were extracted, which were used for training machine learning algorithms.

 

A form of artificial intelligence (AI), a machine learning algorithm learns to detect patterns in the data it is trained on to make predictions.

 

The AI model that the team developed was thus able to predict depressive, manic, and hypomanic episodes with an accuracy of 80 per cent, 98 per cent and 95 per cent, respectively.

 

"Using mathematical modelling to longitudinal data from 168 patients, we derived 36 sleep and circadian rhythm features. These features enabled accurate next-day predictions for depressive, manic, and hypomanic episodes," the authors wrote.

 

The researchers found that daily changes in circadian rhythms are a key predictor of mood episodes.

 

Specifically, delayed circadian rhythms, falling asleep and waking up later in the day, increase the risk of depressive episodes. On the other hand, advanced circadian rhythms -- sleeping and waking up earlier in the day, increase the risk of manic episodes, the researchers said.

 

"Notably, daily circadian phase shifts were the most significant predictors: delays linked to depressive episodes and advances to manic episodes," the authors of the study added.