BackgroundThere is a critical need for real-time tracking of behavioral indicators of mental disorders. Mobile sensing platforms that objectively and noninvasively collect, store, and analyze behavioral indicators have not yet been clinically validated or scalable.ObjectiveThe aim of our study was to report on models of clinical symptoms for post-traumatic stress disorder (PTSD) and depression derived from a scalable mobile sensing platform.MethodsA total of 73 participants (67% [49/73] male, 48% [35/73] non-Hispanic white, 33% [24/73] veteran status) who reported at least one symptom of PTSD or depression completed a 12-week field trial. Behavioral indicators were collected through the noninvasive mobile sensing platform on participants’ mobile phones. Clinical symptoms were measured through validated clinical interviews with a licensed clinical social worker. A combination hypothesis and data-driven approach was used to derive key features for modeling symptoms, including the sum of outgoing calls, count of unique numbers texted, absolute distance traveled, dynamic variation of the voice, speaking rate, and voice quality. Participants also reported ease of use and data sharing concerns.ResultsBehavioral indicators predicted clinically assessed symptoms of depression and PTSD (cross-validated area under the curve [AUC] for depressed mood=.74, fatigue=.56, interest in activities=.75, and social connectedness=.83). Participants reported comfort sharing individual data with physicians (Mean 3.08, SD 1.22), mental health providers (Mean 3.25, SD 1.39), and medical researchers (Mean 3.03, SD 1.36).ConclusionsBehavioral indicators passively collected through a mobile sensing platform predicted symptoms of depression and PTSD. The use of mobile sensing platforms can provide clinically validated behavioral indicators in real time; however, further validation of these models and this platform in large clinical samples is needed.

Background Advances in mobile health (mHealth) technology have made it possible for patients and health care providers to monitor and track behavioral health symptoms in real time. Ideally, mHealth apps include both passive and interactive monitoring and demonstrate high levels of patient engagement. Digital phenotyping, the measurement of individual technology usage, provides insight into individual behaviors associated with mental health. Objective Researchers at a Veterans Affairs Medical Center and Cogito Corporation sought to explore the feasibility and acceptability of an mHealth app, the Cogito Companion. Methods A mixed methodological approach was used to investigate the feasibility and acceptability of the app. Veterans completed clinical interviews and self-report measures, at baseline and at a 3-month follow-up. During the data collection period, participants were provided access to the Cogito Companion smartphone app. The mobile app gathered passive and active behavioral health indicators. Data collected (eg, vocal features and digital phenotyping of everyday social signals) are analyzed in real time. Passive data collected include location via global positioning system (GPS), phone calls, and SMS text message metadata. Four primary model scores were identified as being predictive of the presence or absence of depression or posttraumatic stress disorder (PTSD). Veterans Affairs clinicians monitored a provider dashboard and conducted clinical outreach when indicated. Results Findings suggest that use of the Cogito Companion app was feasible and acceptable. Veterans (n=83) were interested in and used the app; however, active use declined over time. Nonetheless, data were passively collected, and outreach occurred throughout the study period. On the Client Satisfaction Questionnaire–8, 79% (53/67) of the sample reported scores demonstrating acceptability of the app (mean 26.2, SD 4.3). Many veterans reported liking specific app features (day-to-day monitoring) and the sense of connection they felt with the study clinicians who conducted outreach. Only a small percentage (4/67, 6%) reported concerns regarding personal privacy. Conclusions Feasibility and acceptability of the Cogito Corporation platform to monitor mental health symptoms, behaviors, and facilitate follow-up in a sample of veterans were supported. Clinically, platforms such as the Cogito Companion system may serve as useful methods to promote monitoring, thereby facilitating early identification of risk and mitigating negative psychiatric outcomes, such as suicide.

Analyzed 1 Lost to follow-up 26 Analyzed 1 Lost to follow-up 33 Allocated to usual care 28 Received allocated intervention 7 Did not receive allocated intervention 7 Enrolled in study for <150 d when study ended 27 Received allocated intervention 6 Did not receive allocated intervention 6 Enrolled in study for <150 d when study ended Open Access. This is an open access article distributed under the terms of the CC-BY-NC-ND License.

BACKGROUND Advances in mobile health (mHealth) technology have made it possible for patients and providers to monitor and track symptoms in real-time. Ideally, mHealth application (apps) would include both passive and interactive aspects of symptom monitoring. OBJECTIVE Researchers at a Veterans Affairs Medical Center and the Cogito Corporation sought to explore the acceptability and feasibility of such a mHealth app, the Companion System, among Veterans. METHODS A mixed methodological approach was used to investigate acceptability and feasibility. Veterans completed clinical interviews and self-report measures at baseline and a three-month follow-up. Veterans were able to use the Companion System app for three months. Passive data monitoring and outreach also occurred during this time period. RESULTS Results suggested that use of the Companion System was feasible and acceptable. Veterans were interested in, and used, the app; however, use of the app declined over time. Nonetheless, data was passively collected, and outreach occurred throughout. On the Client Satisfaction Questionnaire, 79% of the sample reported satisfaction (M = 26.2, SD = 4.3) demonstrating acceptability. Many Veterans reported liking the app features and the sense of connection they felt with the study clinicians who monitored their symptoms. Lack of privacy was a relatively minor concern. CONCLUSIONS Feasibility and acceptability of a smartphone app to monitor mental health symptoms and follow-up in a Veteran sample was supported. Clinically, the Companion System app may serve as a useful method to promote symptom monitoring and facilitate early identification of risk and mitigation of negative psychiatric outcomes such as suicide.