The COVID-19 pandemic led to a surge in mental health problems, with about one billion people globally affected by various psychiatric conditions. Korea is particularly impacted, with 1.8 million people suffering from depression and anxiety. Over the past five years, the number of patients with clinical mental health disorders in Korea has risen by 37%, totaling around 4.65 million.
In response to this growing crisis, a research team from Korea and the United States has developed a technology that uses biometric data from wearable devices to predict a person’s mood and even identify early signs of depression. This breakthrough could prove especially valuable for shift workers, who are at high risk of mental health issues due to irregular sleep patterns and stress.
On January 15th, KAIST (Korea Advanced Institute of Science and Technology) announced that its team, led by Professor Dae Wook Kim from the Department of Brain and Cognitive Sciences, in collaboration with Professor Daniel B. Forger from the University of Michigan’s Department of Mathematics, has created a system that predicts mood swings and potential symptoms of depression in shift workers. The technology uses data such as activity levels and heart rates, gathered from smartwatches, to detect signs of sleep disorders, loss of appetite, overeating, and difficulties with concentration—symptoms commonly associated with depression.
According to the World Health Organization (WHO), an emerging approach to treating mental illnesses targets the sleep and circadian systems in the brain, which are crucial for emotional regulation, decision-making, and overall mood. Traditionally, measuring these internal rhythms and sleep states has been difficult, requiring invasive methods like blood or saliva samples every 30 minutes during sleep, along with expensive tests such as polysomnography (PSG). PSG, which can cost up to $1,000, has made it difficult for many, especially those in disadvantaged communities, to access effective mental health care.
To overcome these barriers, the research team explored using wearable devices to collect biometric data in real-time. These devices are already capable of tracking heart rate, body temperature, and activity levels without the need for hospital visits or expensive tests. However, most current wearables only provide limited, indirect information about biomarkers such as the phase of the circadian clock, which is crucial for understanding mood and mental health.
To address this limitation, the team developed a filtering technology capable of estimating the circadian rhythm phase with high accuracy. By analyzing heart rate and activity data from smartwatches, the system creates a “digital twin” of the brain’s circadian rhythm, providing a precise estimate of any disruptions in the system. This breakthrough allows for a more accurate prediction of mood changes and symptoms of depression.
The new technology was tested in collaboration with the University of Michigan’s research team, led by Professors Srijan Sen and Amy Bohnert. In a large-scale study involving around 800 shift workers, the team demonstrated that this digital circadian rhythm biomarker could predict not only mood changes for the following day but also six key symptoms of depression, including sleep disturbances, changes in appetite, reduced concentration, and even suicidal thoughts.
This innovative approach to mental health monitoring has the potential to revolutionize the treatment of depression and other psychiatric conditions, particularly for shift workers, who are often left without proper care due to the limitations of current medical technology. With the ability to predict mood changes in advance, this wearable-based system could lead to more effective and accessible treatments for those struggling with mental health issues.
Related articles:
- How To Treat Teenage Depression At Home?
- 10 Things You Can Say To Someone With Depression
- Is Alcohol Good For Depression And Anxiety?
