The coronavirus pandemic has also triggered a pandemic of mental illness. Worldwide, approximately one billion people suffer from various psychiatric illnesses. Korea is one of the more severe cases, with about 1.8 million patients suffering from depression and anxiety disorders, and the total number of patients with clinical mental illnesses has increased by 37% to about 4.65 million in five years. A joint research team from Korea and the United States has developed a technology that uses biometric data collected via wearable devices to predict tomorrow’s mood and, in addition, to predict the possibility of developing symptoms of depression.

Innovative Wearable Devices Use the Circadian Rhythm to Predict Symptoms of Depression

KAIST (President Kwang Hyung Lee) announced on January 15 that the research team led by Professor Dae Wook Kim of the Department of Brain and Cognitive Sciences and the team led by Professor Daniel B. Forger of the Department of Mathematics at the University of Michigan in the United States have developed a technology to predict symptoms of depression, such as sleep disorders, depression, loss of appetite, overeating, and lack of concentration in shift workers, using activity and heart rate data collected by smartwatches. According to the WHO, a promising new treatment for mental illness focuses on sleep and the circadian timing system in the brain’s hypothalamus, which directly affects impulsivity, emotional responses, decision-making and overall mood.

However, measuring endogenous circadian rhythms and sleep states requires taking blood or saliva samples every 30 minutes throughout the night to measure changes in the concentration of the melatonin hormone in our body, and conducting a polysomnography (PSG). Since such treatments require hospitalization and most mental health patients only come for outpatient treatment, there has been no significant progress in developing treatment methods that take these two factors into account. Furthermore, the cost of the PSG test is very expensive.

The solution to overcome these problems is to use portable devices that can more easily collect biometric data such as heart rate, body temperature, and activity level in real time and without spatial restrictions. However, the current portable devices have the limitation that they only provide indirect information about the biomarkers needed by medical personnel, such as the phase of the circadian clock. The joint research team developed a filtering technology that accurately estimates the phase of the circadian clock, which changes daily, such as heart rate and activity time series data collected by a smartwatch. This is an implementation of a digital twin that precisely describes the 24-hour rhythm in the brain and can be used to estimate circadian rhythm disturbances.

Non-Invasive Mental Health Monitoring Technology

The possibility of using the digital twin of this circadian clock to predict symptoms of depression was verified in collaboration with the research team of Professor Srijan Sen of the Michigan Neuroscience Institute and Professor Amy Bohnert of the University of Michigan Department of Psychiatry. The joint research team conducted a large-scale prospective cohort study of approximately 800 shift workers and showed that the digital biomarker for circadian rhythm disruption estimated by the technology can predict tomorrow’s mood as well as six symptoms, including sleep problems, changes in appetite, inability to concentrate, and suicidal thoughts, which are representative symptoms of depression.

Experts expect that this research will be able to present a continuous and non-invasive mental health monitoring technology. This is expected to provide a new paradigm for mental health care. By solving some of the key problems faced by socially disadvantaged people in current treatment practices, it may enable them to take more active steps when they experience symptoms of depression, such as seeking counseling before things get out of hand.