Personal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning

Abstract

Sensors in everyday devices, such as our phones, wearables, and computers, leave a stream of digital traces. Personal sensing refers to collecting and analyzing data from sensors embedded in the context of daily life with the aim of identifying human behaviors, thoughts, feelings, and traits. This article provides a critical review of personal sensing research related to mental health, focused principally on smartphones, but also including studies of wearables, social media, and computers. We provide a layered, hierarchical model for translating raw sensor data into markers of behaviors and states related to mental health. Also discussed are research methods as well as challenges, including privacy and problems of dimensionality. Although personal sensing is still in its infancy, it holds great promise as a method for conducting mental health research and as a clinical tool for monitoring at-risk populations and providing the foundation for the next generation of mobile health (or mHealth) interventions.

Smartphone app to investigate the relationship between social connectivity and mental health

“…Social network factors are known to be critically important for mental health, and studies involving a larger sample size are needed to reliably identify social network features that are predictive of mental illness such as depression, anxiety and suicidality [19]. This kind of objective information has the capacity to improve the detection of mental illness using objective social network indices [20], provide risk factors for suicidality by detecting social withdrawal [21], as well as potentially suggest novel avenues for intervention.…”

Ecological momentary interventions for depression and anxiety

“…First, EMIs should make greater use of the ability to understand people's mental health state through passive detection derived from sensors. Several small studies have demonstrated proof-of-concept that sensors can be used to predict aspects of people's mental health (Mohr, Zhang, & Schueller, 2017). The EMIs of the future might not need to ask people what they need, but be able to tell them based on their ability to collect and process passive data.…”

Health Care Provider Perceptions of Consumer-Grade Devices and Apps for Tracking Health: A Pilot Study (Preprint)

“…Recently, the use of technology to more accurately track health indicators has increased; consumer-grade sensor devices (e.g., Fitbit) and Web/smartphone-based applications (e.g., MyFitnessPal) (apps) that allow patients to track physical activity, diet, sleep, and a variety of other factors (referred to as "technologies" throughout) have proliferated. Using these technologies have been associated with positive health outcomes across a wide range of conditions and behaviors, such as diet, physical activity, weight management, and mental health [10,11]. With this increased use of technologies for self-tracking of health behaviors, there are many implications for use of this data in the clinical setting.…”