JMIR Publications

ABSTRACT

Background:

Current methods of predicting mental health crises usually rely on subjective symptom ratings obtained at discrete time points during routine clinical care. But clinical decision-making based on such subjective information is challenging, as changes in symptoms might be sub-threshold, context dependent, or variable over time. Therefore, novel prediction tools need to be developed meeting the highest standards of reliability, feasibility, scalability, and affordability. Smartphones might configure such prediction tools, as they are ubiquitous and afford a wide variety of types of behavioural data that can be automatically recorded by their built-in sensors.

Objective:

To facilitate the collection of high-quality, passive mobile sensing data, we built the Predicting Risk and Outcomes of Social InTeractions (PROSIT) tool, a mobile sensing app that runs on both Android and iOS operating systems. In addition we aimed to ensure the acceptability and usability of this tool in youth.

Methods:

The PROSIT tool captures multiple indices of a youth’s daily life behaviors via their naturalistic use of a smartphone. These indices include physical activity, geolocation, sleep, phone use, typed text, music choice, and acoustic vocal quality. Importantly, the PROSIT tool records most of these data passively with only minimal burden to youth. All the time-intensive, detail-rich data streams that the tool captures to make inferences about youth’s mental health states are encrypted and uploaded to a secure server at our clinic. Although other mobile data collection tools exist, the PROSIT tool places a unique emphasis on the designing the tool for youth.

Results:

In a pilot study (N=61), participants tolerated the PROSIT tool well, reporting only minimal burden. Over 85% of youth were using the tool for the whole study period, although they were suffering from severe clinical symptomatology. But not only youth accepted the PROSIT tool well, for youth under the age of 15 we requested consent of parents, which 80% of parents provided.

Conclusions:

The PROSIT tool offers novel way for clinical monitoring in youth with mental disorder. The high acceptability rates indicate that mobile sensing technologies can successfully be used even in youth with severe clinical symptomatology. We built the PROSIT tool to assist in clinical monitoring, with the ultimate goal of leveraging individual big data to empower youth patients to take on a more active role in the management of their clinical symptomatology.