Fostering mental wellness: Early detection of depression by using a wearable device.

Depression or mood disorder is a common illness that impacts mentally, depression affects the way people act and think. Depression is identified by a loss of pleasure and interest in activities they usually enjoy. In the present century, technology has been remarked upon internationally in various fields, especially health care and mental health. Previous researchers described physical activities and sleeping patterns as used methodology to predict the risk of depression, but social avoidance was never minded. Social interaction avoidance can indeed contribute to feelings of depression and exacerbate existing depressive symptoms. In this research, we have proposed an integrated system (wearable device+chatbot and Machine Learning) to detect early depression using a mobile application linked with wearable device APIs that can predict a chance of getting depression by using machine learning, as well as social interaction activities including several interactions with friends or family where we will use chatbot to get some data related to social interactions and emotions. Qualitative-cum-quantitative data collection methods have been considered. The proposed model correctly predicted 0.88% of depressed people with an accuracy of 0.96%, which shows that it can be helpful in depression prevention. As an outcome of this research, there is a benefit from regular personalized well-being advice delivered through this technology, resulting in increased productivity and a stronger sense of purpose as feelings of worthlessness diminish. [ABSTRACT FROM AUTHOR]