Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders

Abstract

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.

Digital Technology Disorder: Justification and a Proposed Model of Treatment

“…Since -early recognition of sub-syndromal mood and anxiety symptoms'' is paramount in lessening -the pernicious impact of chronic psychological distress and loss of function'' [62], there is a need for timely monitoring of disorder subjects' behaviour. Utilising multifarious digital touchpoints on smartphones can allow for ‗behavioural indicators' to be collected and interpreted promptly [62].…”

“…Utilising multifarious digital touchpoints on smartphones can allow for ‗behavioural indicators' to be collected and interpreted promptly [62]. This is due to digital phenotyping (DP), which involves -moment-by-moment quantification of the individual-level human phenotype in situ using data from personal digital devices‖ [78].…”

“…This is because -digital fingerprints'' are thought to -reflect the lived experiences of people in their natural environments'' [57], thus giving DP the potential to reveal key behavioural insights on a granular level. Utilising -digital trace data… collected from sensors embedded on mobile devices'' [62], DP could gather both active and passive patient data. Active refers to elements that require participation from the user, such as online survey responses or recorded speech samples [78].…”

“…For example, speech recordings -could be used to detect vocal markers of mood'' [57]. By analysing -lexical content'', -prosody, voice quality‖' and the -overall tone of voice'', these -vocal cues can provide valuable insights into physical and mental states'' [62].…”

“…In [62] note that passive data -can enable the identification and tracking'' of phenomena such as -mood, fatigue, social connectedness'' and -physical isolation''. By monitoring, for example, a fluctuation in sleep levels and dramatic decreases in movement via GPS, DP -could indicate depression symptoms'' [13].…”