The global mental health crisis, exacerbated by the COVID-19 pandemic, has left approximately one billion people worldwide grappling with psychiatric conditions. In South Korea alone, the number of patients suffering from depression and anxiety disorders has surged to around 1.8 million, with a 37% increase in the total number of individuals affected by clinical mental health conditions over the past five years, bringing the total to approximately 4.65 million.
In an innovative breakthrough, a collaborative research team from South Korea and the United States has developed a promising technology that predicts mood fluctuations and the potential onset of depression symptoms using biometric data from wearable devices.
On January 15th, KAIST (Korea Advanced Institute of Science and Technology) announced the groundbreaking work led by Professor Dae Wook Kim from the Department of Brain and Cognitive Sciences, in partnership with Professor Daniel B. Forger from the Department of Mathematics at the University of Michigan. This research utilizes activity and heart rate data collected from smartwatches to forecast depression-related symptoms such as sleep disturbances, appetite changes, overeating, and diminished concentration, particularly among shift workers.
According to the World Health Organization (WHO), mental health treatments are increasingly focusing on the brain’s hypothalamus, which controls the sleep and circadian timekeeping system—key factors in regulating emotional responses, decision-making, and mood. However, measuring the body’s circadian rhythms and sleep states traditionally involves blood or saliva tests every 30 minutes throughout the night, as well as a costly procedure known as polysomnography (PSG), which typically costs around $1,000. This makes such treatments inaccessible to many, especially those in socially disadvantaged communities.
The joint research team’s solution overcomes these barriers by using wearable devices to collect biometric data in real time, including heart rate, body temperature, and activity levels, without the need for specialized equipment or hospitalization. Current wearable devices, however, have limitations, as they only provide indirect data related to the circadian clock, which is critical for medical professionals.
To address this issue, the team developed a filtering technology that accurately estimates the phase of the circadian clock from smartwatch-collected data, such as heart rate and activity patterns. This process creates a “digital twin” of the circadian rhythm in the brain, enabling the estimation of circadian disruptions and their potential impact on mental health.
The team collaborated with the research groups of Professors Srijan Sen and Amy Bohnert from the University of Michigan to validate the technology’s efficacy. A large-scale prospective cohort study involving 800 shift workers demonstrated that the digital biomarker generated by this technology can predict mood fluctuations and six key depression symptoms—sleep disturbances, appetite changes, concentration issues, and even suicidal thoughts.
This innovative approach offers hope for a more accessible and affordable way to monitor and predict mental health conditions, particularly depression, through the use of wearable technology. It could prove to be a significant step forward in making mental health treatments more effective and inclusive.
Related topic:
Stigma and Lack of Support Fuel Physician Suicides
Autistic TGD Individuals Face Worse Healthcare, Study Reveals
HealthLynked Launches ARi: AI-Powered Healthcare Assistant
