«Traditionally, researchers have relied on questionnaire data administered by a clinician or self-reported to assess an individual’s mental health. However, these methods may be limited in their ability to detect the moment-by-moment changes in psychological factors that is required for preventative measures and rapid interventions. First, questionnaires often take place sporadically, with long intervals between them, during which time symptoms may change considerably. Second, these questionnaires often rely on retrospective evaluations and, as such, are prone to recall bias. Third, there may be a tendency for respondents to provide socially-desirable answers. Finally, patients typically only meet with a clinician or undertake assessments once the symptoms have already progressed to a certain level of severity, making prevention far more challenging.»

«Smartphone devices may offer a unique opportunity to overcome some of these limitations. Equipped with an array of sensors, smartphones unobtrusively provide a continuous stream of data related to an individual’s mental health, including location, smartphone usage behavior, physical activity and social interactions. This moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices is referred to as “digital phenotyping”. There is now a growing body of research demonstrating that digital phenotyping data may enable the identification of people suffering from or at risk of developing mental disorders, in some cases even before symptoms are visible (or detectable) using traditional methods»

Article written by Isaac Moshe, Yannik Terhorst, Kennedy Opoku Asare, Lasse Bosse Sander, Denzil Ferreira, Harald Baumeister, David C. Mohr and Laura Pulkki-Ráback.