Scientists have learned to detect depression according to data from a fitness bracelet
Miscellaneous / / January 25, 2022
Almost any tracker will do.
A group of scientists from the Nanyang Technological University in Singapore developed a predictive computer program that can be used to detect depression. It is based on data from a regular fitness bracelet.
A program called Ycogni works on the basis of machine learning. It assesses the risk of depression by analyzing a person's physical activity, sleep patterns and circadian rhythms based on data from wearable devices. In the study, scientists used Fitbit Charge 2 bracelets.
290 subjects wore trackers for 14 days. They could only be removed while taking a bath or shower, as well as for recharging.
At the beginning and then again at the end of the two-week period, participants also filled out a questionnaire that is widely used to identify depressive disorders. The results of these surveys were combined with data collected by the Fitbit Charge 2 and used to train Ycogni.
After training, when this program was used to analyze the bracelet data alone, it was found to be about 80% accurate in predicting the development of depression.
It was noted that in people at risk, the heart rate was more variable between 2 and 4 am, and then again between 4 and 6 am. This is consistent with earlier studies suggesting that changes in heart rate during sleep may be a strong physiological indicator of depression.
In addition, Fitbit bracelets confirmedthat at-risk subjects tended to have a wider range of waking and sleeping times. Which is also an indicator of a possible disorder.
Our study has successfully shown that we can use wearable device sensor data to help identify people's risk of developing depression. With the growing popularity of wearable devices, one day our software can be used for timely and non-intrusive screening.
Josip Car
Head of Research, Nanyang Technological University
Former Stanford scholars suggested a completely new way to treat depression, which was effective for 79% of patients.
Read alsoš§
- Why evolution hasn't eradicated depression
- Post-vacation depression: how to return from vacation with minimal losses
- Is winter to blame for your bad mood