Unobtrusive monitoring of behavior and movement patterns to detect clinical depression severity level via smartphone.

The number of individuals with mental disorders is increasing and they are commonly found among individuals who avoid social interaction and like to live alone. Amongst such mental health disorders is depression which is both common and serious. The present paper introduces a method to assess the depression level of an individual using a smartphone by monitoring their daily activities. The time domain characteristics from a smartphone acceleration sensor were used alongside a vector machine algorithm to classify physical activities. Additionally, the geographical location information was clustered using a smartphone GPS sensor to simplify movement patterns. A total of 12 features were extracted from individuals' physical activity and movement patterns and were analyzed alongside their weekly depression scores using the nine-item Patient Health Questionnaire. Using a wrapper feature selection method, a subset of features was selected and applied to a linear regression model to estimate the depression score. The support vector machine algorithm was then used to classify the depression severity level among individuals (absence, moderate, severe) and had an accuracy of 87.2% in severe depression cases which outperformed other classification models including the k-nearest neighbor and artificial neural network. This method of identifying depression is a cost-effective solution for long-term use and can monitor individuals for depression without invading their personal space or creating other day-to-day disturbances.