BACKGROUND
Adolescents often experience a heightened incidence of depressive symptoms that can persist without early intervention.[1] Therefore, early detection and timely treatment of depressive symptoms in adolescents are crucial.[2] However, adolescents often struggle to identify these symptoms and even when they are aware of these symptoms, seeking help is not always their immediate response.[3]
OBJECTIVE
This study aimed to explore the relationship between passive digital data, specifically keystroke and stylus data collected via mobile devices, and the manifestation of depressive symptoms.
METHODS
A total of 927 first-year middle school students from a Seoul city-based school solved Korean language and math problems. Throughout this process, 77 types of keystroke and stylus data were collected, including parameters such as the number of key presses, speed, acceleration, length, and pressure. Depressive symptoms were measured using the self-rated PHQ-9.
RESULTS
Multiple regression analysis highlighted the significance of stroke length, speed, acceleration, the average y-coordinate, tap pressure, and the number of incorrect answers in relation to the scores on the depressive scale.
CONCLUSIONS
This study presents an important demonstration of the potential of automatically collected data during school exams or classes for the early screening of students' clinical depressive symptoms.