Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders
Background: There 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. Objective: The aim of our stu...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Gunther Eysenbach, JMIR
2017
|
| Online Access: | http://hdl.handle.net/1721.1/110020 https://orcid.org/0000-0002-8053-9983 |
| _version_ | 1811081203089932288 |
|---|---|
| author | Place, Skyler Blanch-Hartigan, Danielle Rubin, Channah Gorrostieta, Cristina Mead, Caroline Kane, John Marx, Brian P Feast, Joshua Deckersbach, Thilo Nierenberg, Andrew Azarbayejani, Ali Pentland, Alex Paul |
| author2 | Massachusetts Institute of Technology. Media Laboratory |
| author_facet | Massachusetts Institute of Technology. Media Laboratory Place, Skyler Blanch-Hartigan, Danielle Rubin, Channah Gorrostieta, Cristina Mead, Caroline Kane, John Marx, Brian P Feast, Joshua Deckersbach, Thilo Nierenberg, Andrew Azarbayejani, Ali Pentland, Alex Paul |
| author_sort | Place, Skyler |
| collection | MIT |
| description | Background: There 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.
Objective: The 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.
Methods: A 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.
Results: Behavioral 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).
Conclusions: Behavioral 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. |
| first_indexed | 2024-09-23T11:43:04Z |
| format | Article |
| id | mit-1721.1/110020 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:43:04Z |
| publishDate | 2017 |
| publisher | Gunther Eysenbach, JMIR |
| record_format | dspace |
| spelling | mit-1721.1/1100202022-10-01T05:30:26Z Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders Place, Skyler Blanch-Hartigan, Danielle Rubin, Channah Gorrostieta, Cristina Mead, Caroline Kane, John Marx, Brian P Feast, Joshua Deckersbach, Thilo Nierenberg, Andrew Azarbayejani, Ali Pentland, Alex Paul Massachusetts Institute of Technology. Media Laboratory Pentland, Alex Paul Background: There 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. Objective: The 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. Methods: A 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. Results: Behavioral 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). Conclusions: Behavioral 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. United States. Defense Advanced Research Projects Agency (contract N66001-11-C-4094) 2017-06-19T19:02:58Z 2017-06-19T19:02:58Z 2017-03 2016-12 Article http://purl.org/eprint/type/JournalArticle 1438-8871 http://hdl.handle.net/1721.1/110020 Place, Skyler; Blanch-Hartigan, Danielle; Rubin, Channah; Gorrostieta, Cristina; Mead, Caroline; Kane, John; Marx, Brian P et al. “Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders.” Journal of Medical Internet Research 19, no. 3 (March 2017): e75 © 2017 Place et al https://orcid.org/0000-0002-8053-9983 en_US http://dx.doi.org/10.2196/jmir.6678 Journal of Medical Internet Research Creative Commons Attribution 2.0 License http://www.creativecommons.org/licenses/by/2.0/ application/pdf Gunther Eysenbach, JMIR JMIR Publications |
| spellingShingle | Place, Skyler Blanch-Hartigan, Danielle Rubin, Channah Gorrostieta, Cristina Mead, Caroline Kane, John Marx, Brian P Feast, Joshua Deckersbach, Thilo Nierenberg, Andrew Azarbayejani, Ali Pentland, Alex Paul Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title | Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title_full | Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title_fullStr | Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title_full_unstemmed | Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title_short | Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders |
| title_sort | behavioral indicators on a mobile sensing platform predict clinically validated psychiatric symptoms of mood and anxiety disorders |
| url | http://hdl.handle.net/1721.1/110020 https://orcid.org/0000-0002-8053-9983 |
| work_keys_str_mv | AT placeskyler behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT blanchhartigandanielle behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT rubinchannah behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT gorrostietacristina behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT meadcaroline behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT kanejohn behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT marxbrianp behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT feastjoshua behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT deckersbachthilo behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT nierenbergandrew behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT azarbayejaniali behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders AT pentlandalexpaul behavioralindicatorsonamobilesensingplatformpredictclinicallyvalidatedpsychiatricsymptomsofmoodandanxietydisorders |