SG scientists are developing a computer program that can detect people at higher risk for depression

SINGAPORE: Scientists at Nanyang Technological University in Singapore (NTU) have developed a computer program that can detect people at higher risk of developing depression.

The predictive program analyzes a person’s physical activity, sleep patterns and circadian rhythms using data from wearable devices, such as Fitbit watches.

A 2019 three-month trial of 290 adults showed the program was 80% accurate in detecting people with depression (or at high risk of developing depressive symptoms/depression) compared to healthy people .

The trial participants were adults between the ages of 21 and 69 and wore a tracker for two weeks. The average age was 33 years old.

Professor Josip Car, director of the Center for Population Health Sciences at the Lee Kong Chian School of Medicine, who led the study, said Monday (January 24) that to refine and improve the machine learning algorithm, the team plans larger studies of more than 1,000 participants followed over a two-year period.

Anyone can take part in the study and there are no selection criteria, Professor Car added.

Depression affects 264 million people worldwide and goes undiagnosed or untreated in half of cases, according to the World Health Organization’s website.

The Institute of Mental Health said in August last year that a study of more than 1,000 participants found that 13% had reported symptoms of anxiety or depression during the Covid-19 pandemic.

Commenting on the NTU study, Professor Car said: “Our study successfully showed that we could exploit data from wearable devices, and given the growing popularity of these wearable devices, they could be used for a rapid and discreet screening for depression.”

Almost a billion people wear activity trackers.

The researchers cautioned that their program is not intended to predict an individual’s likelihood of suffering from depression, but rather to detect whether a person is at high risk of suffering from depression at the current time.

The team also found that certain behavior patterns in a person can be associated with depressive symptoms, such as feelings of helplessness and hopelessness, loss of interest in daily activities, and changes in appetite or weight.

Those who had more varied heart rhythms between 2 a.m. and 4 a.m. and between 4 a.m. and 6 a.m. were likely to have more severe depressive symptoms.

This confirms the results of previous studies, which found that changes in heart rate during sleep may be a valid physiological marker of depression.

Less regular sleep patterns, such as variable wake-up times and bedtimes, are also associated with a higher tendency to have depressive symptoms.

Although the rhythms of the week are primarily determined by work routines, a person’s ability to follow these routines differs between depressed and healthy individuals. Those who are in good health are more regular when they wake up and fall asleep.

“We look forward to expanding our research to include other vital signs in detecting depression risk, such as skin temperature. The development of our program could help facilitate early, discreet, continuous and cost-effective detection of depression in the general population,” said Professor Car.

Associate Professor Georgios Christopoulos, from NTU’s Nanyang Business School, who co-led the study, said: “Our team will also work on extending it to other types of psychological state, such as mental fatigue. The program could also be customized in the future.

The results of the study have been published in a peer-reviewed academic journal JMIR mHealth and uHealth in November last year. – The Straits Times (Singapore)/Asia News Network

Gordon K. Morehouse