Abstract
There are rising rates of depression on college campuses. Mental health services on our campuses are working at full stretch. In response researchers have proposed using mobile sensing for continuous mental health assessment. Existing work on understanding the relationship between mobile sensing and depression, however, focuses on generic behavioral features that do not map to major depressive disorder symptoms defined in the standard mental disorders diagnostic manual (DSM-5). We propose a new approach to predicting depression using passive sensing data from students' smartphones and wearables. We propose a set of symptom features that proxy the DSM-5 defined depression symptoms specifically designed for college students. We present results from a study of 83 undergraduate students at Dartmouth College across two 9-week terms during the winter and spring terms in 2016. We identify a number of important new associations between symptom features and student self reported PHQ-8 and PHQ-4 depression scores. The study captures depression dynamics of the students at the beginning and end of term using a pre-post PHQ-8 and week by week changes using a weekly administered PHQ-4. Importantly, we show that symptom features derived from phone and wearable sensors can predict whether or not a student is depressed on a week by week basis with 81.5% recall and 69.1% precision.
- Saeed Abdullah, Mark Matthews, Ellen Frank, Gavin Doherty, Geri Gay, and Tanzeem Choudhury. 2016. Automatic detection of social rhythms in bipolar disorder. Journal of the American Medical Informatics Association 23, 3 (2016), 538--543.Google ScholarCross Ref
- Sharifa Alghowinem, Roland Goecke, Michael Wagner, Julien Epps, Matthew Hyett, Gordon Parker, and Michael Breakspear. 2016. Multimodal Depression Detection: Fusion Analysis of Paralinguistic, Head Pose and Eye Gaze Behaviors. IEEE Transactions on Affective Computing (2016).Google Scholar
- American College Health Association. 2016. American College Health Association-National College Health Assessment II: Reference Group Executive Summary Fall 2016. Hanover, MD: American College Health Association (2016).Google Scholar
- Apple. 2017. Core Motion. (2017). https://developer.apple.com/reference/coremotion.Google Scholar
- American Psychiatric Association et al. 2013. Diagnostic and statistical manual of mental disorders (DSM-5®). American Psychiatric Pub.Google Scholar
- Min Aung, Faisal Alquaddoomi, Cheng-Kang Hsieh, Mashfiqui Rabbi, Longqi Yang, JP Pollak, Deborah Estrin, and Tanzeem Choudhury. 2016. Leveraging Multi-Modal Sensing for Mobile Health: a Case Review in Chronic Pain. IEEE Journal of Selected Topics in Signal Processing 10, 5 (2016), 1--13.Google ScholarCross Ref
- P Bech, N-A Rasmussen, L Raabaek Olsen, V Noerholm, and W Abildgaard. 2001. The sensitivity and specificity of the Major Depression Inventory, using the Present State Examination as the index of diagnostic validity. Journal of affective disorders 66, 2 (2001), 159--164.Google ScholarCross Ref
- Aaron T Beck, David Guth, Robert A Steer, and Roberta Ball. 1997. Screening for major depression disorders in medical inpatients with the Beck Depression Inventory for Primary Care. Behaviour research and therapy 35, 8 (1997), 785--791.Google Scholar
- Aaron T Beck, Robert A Steer, Gregory K Brown, et al. 1996. Beck depression inventory. (1996).Google Scholar
- Dror Ben-Zeev, Christopher J Brenner, Mark Begale, Jennifer Duffecy, David C Mohr, and Kim T Mueser. 2014. Feasibility, acceptability, and preliminary efficacy of a smartphone intervention for schizophrenia. Schizophrenia bulletin (2014), sbu033.Google Scholar
- Dror Ben-Zeev, Rui Wang, Saeed Abdullah, Rachel Brian, Emily A Scherer, Lisa A Mistier, Marta Hauser, John M Kane, Andrew Campbell, and Tanzeem Choudhury. 2015. Mobile behavioral sensing for outpatients and inpatients with schizophrenia. Psychiatric services 67, 5 (2015), 558--561.Google Scholar
- Dror Ben-Zeev, Michael A Young, and Patrick W Corrigan. 2010. DSM-V and the stigma of mental illness. Journal of Mental Health 19, 4 (2010), 318--327.Google ScholarCross Ref
- Alison L Calear and Helen Christensen. 2010. Systematic review of school-based prevention and early intervention programs for depression. Journal of adolescence 33, 3 (2010), 429--438.Google ScholarCross Ref
- Luca Canzian and Mirco Musolesi. 2015. Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis. In Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 1293--1304. Google ScholarDigital Library
- Zhenyu Chen, Mu Lin, Fanglin Chen, Nicholas D Lane, Giuseppe Cardone, Rui Wang, Tianxing Li, Yiqiang Chen, Tonmoy Choudhury, and Andrew T Campbell. 2013. Unobtrusive sleep monitoring using smartphones. In 2013 7th International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth). IEEE, 145--152. Google ScholarDigital Library
- Tanzeem Choudhury, Sunny Consolvo, Beverly Harrison, Jeffrey Hightower, Anthony LaMarca, Louis LeGrand, Ali Rahimi, Adam Rea, G Borriello, Bruce Hemingway, et al. 2008. The mobile sensing platform: An embedded activity recognition system. IEEE Pervasive Computing 7, 2 (2008). Google ScholarDigital Library
- Philip I Chow, Karl Fua, Yu Huang, Wesley Bonelli, Haoyi Xiong, Laura E Barnes, and Bethany A Teachman. 2017. Using Mobile Sensing to Test Clinical Models of Depression, Social Anxiety, State Affect, and Social Isolation Among College Students. Journal of medical Internet research 19, 3 (2017).Google ScholarCross Ref
- Patrick Corrigan and Alicia Matthews. 2003. Stigma and disclosure: Implications for coming out of the closet. Journal of mental health 12, 3 (2003), 235--248.Google ScholarCross Ref
- Dartmouth College Office of Institutional Research. 2016. Dartmouth Student Health Survey. (2016). http://www.dartmouth.edu/oir/2016-dartmouth-health-survey-final-web-version.pdf.Google Scholar
- Kadir Demirci, Mehmet Akgönül, and Abdullah Akpinar. 2015. Relationship of smartphone use severity with sleep quality, depression, and anxiety in university students. Journal of behavioral addictions 4, 2 (2015), 85--92.Google ScholarCross Ref
- Olive Jean Dunn. 1961. Multiple comparisons among means. J. Amer. Statist. Assoc. 56, 293 (1961), 52--64.Google ScholarCross Ref
- Daniel Eisenberg, Ezra Golberstein, and Sarah E Gollust. 2007. Help-seeking and access to mental health care in a university student population. Medical care 45, 7 (2007), 594--601.Google ScholarCross Ref
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In KDD '96. AAAI Press, 226--231. Google ScholarDigital Library
- Asma Ahmad Farhan, Chaoqun Yue, Reynaldo Morillo, Shweta Ware, Jin Lu, Jinbo Bi, Jayesh Kamath, Alexander Russell, Athanasios Bamis, and Bing Wang. 2016. Behavior vs. Introspection: Refining prediction of clinical depression via smartphone sensing data. In 7th Conference on Wireless Health, WH.Google ScholarCross Ref
- Jerome H. Friedman. 2001. Greedy Function Approximation: A Gradient Boosting Machine. The Annals of Statistics 29, 5 (2001), 1189--1232. http://www.jstor.org/stable/2699986Google ScholarCross Ref
- Susan R Furr, John S Westefeld, Gaye N McConnell, and J Marshall Jenkins. 2001. Suicide and depression among college students: A decade later. Professional Psychology: Research and Practice 32, 1 (2001), 97.Google ScholarCross Ref
- Steven J Garlow, Jill Rosenberg, J David Moore, Ann P Haas, Bethany Koestner, Herbert Hendin, and Charles B Nemeroff. 2008. Depression, desperation, and suicidal ideation in college students: results from the American Foundation for Suicide Prevention College Screening Project at Emory University. Depression and anxiety 25, 6 (2008), 482--488.Google Scholar
- Ginger.io. 2017. Ginger.io. (2017). https://ginger.io/.Google Scholar
- Google Activity Recognition Api. 2017. Google Activity Recognition Api. https://developers.google.com/android/reference/com/google/android/gms/location/ActivityRecognitionApi. (2017).Google Scholar
- Max Hamilton. 1960. A rating scale for depression. Journal of neurology, neurosurgery, and psychiatry 23, 1 (1960), 56.Google ScholarCross Ref
- James A Hanley and Barbara J McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143, 1 (1982), 29--36.Google ScholarCross Ref
- C Haring, R Banzer, A Gruenerbl, S Oehler, G Bahle, P Lukowicz, and O Mayora. 2015. Utilizing Smartphones as an Effective Way to Support Patients with Bipolar Disorder: Results of the Monarca Study. European Psychiatry 30 (2015), 558.Google ScholarCross Ref
- Treniece Lewis Harris and Sherry Davis Molock. 2000. Cultural orientation, family cohesion, and family support in suicide ideation and depression among African American college students. Suicide and Life-Threatening Behavior 30, 4 (2000), 341--353.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Joel W Hughes and Catherine M Stoney. 2000. Depressed mood is related to high-frequency heart rate variability during stressors. Psychosomatic medicine 62, 6 (2000), 796--803.Google Scholar
- Thomas Insel, Bruce Cuthbert, Marjorie Garvey, Robert Heinssen, Daniel S Pine, Kevin Quinn, Charles Sanislow, and Philip Wang. 2010. Research domain criteria (RDoC): toward a new classification framework for research on mental disorders. (2010).Google Scholar
- Richard Kadison and Theresa Foy DiGeronimo. 2004. College of the overwhelmed: The campus mental health crisis and what to do about it. Jossey-Bass.Google Scholar
- Andrew H Kemp and Daniel S Quintana. 2013. The relationship between mental and physical health: insights from the study of heart rate variability. International Journal of Psychophysiology 89, 3 (2013), 288--296.Google ScholarCross Ref
- Michael J Kozak and Bruce N Cuthbert. 2016. The NIMH research domain criteria initiative: background, issues, and pragmatics. Psychophysiology 53, 3 (2016), 286--297.Google ScholarCross Ref
- Kurt Kroenke and Robert L Spitzer. 2002. The PHQ-9: a new depression diagnostic and severity measure. Psychiatric Annals 32, 9 (2002), 509--515.Google ScholarCross Ref
- Kurt Kroenke, Robert L Spitzer, and Janet BW Williams. 2001. The PHQ-9. Journal of general internal medicine 16, 9 (2001), 606--613.Google ScholarCross Ref
- Kurt Kroenke, Robert L Spitzer, Janet BW Williams, and Bernd Löwe. 2009. An ultra-brief screening scale for anxiety and depression: the PHQ--4. Psychosomatics 50, 6 (2009), 613--621.Google Scholar
- Kurt Kroenke, Tara W Strine, Robert L Spitzer, Janet BW Williams, Joyce T Berry, and Ali H Mokdad. 2009. The PHQ-8 as a measure of current depression in the general population. Journal of affective disorders 114, 1 (2009), 163--173.Google ScholarCross Ref
- Min Kwon, Dai-Jin Kim, Hyun Cho, and Soo Yang. 2013. The smartphone addiction scale: development and validation of a short version for adolescents. PloS one 8, 12 (2013), e83558.Google ScholarCross Ref
- Nicholas D Lane, Emiliano Miluzzo, Hong Lu, Daniel Peebles, Tanzeem Choudhury, and Andrew T Campbell. 2010. A survey of mobile phone sensing. Communications Magazine, IEEE 48, 9 (2010), 140--150. Google ScholarDigital Library
- Nicholas D Lane, Mashfiqui Mohammod, Mu Lin, Xiaochao Yang, Hong Lu, Shahid Ali, Afsaneh Doryab, Ethan Berke, Tanzeem Choudhury, and Andrew Campbell. 2011. Bewell: A smartphone application to monitor, model and promote wellbeing. In 5th international ICST conference on pervasive computing technologies for healthcare. 23--26.Google ScholarCross Ref
- Georgia Tech Campus Life. 2017. Campus Life | Optimizing the Student Environment. (2017). http://www.quantifiedcampus.gatech.edu/.Google Scholar
- Marek Malik. 1996. Heart rate variability. Annals of Noninvasive Electrocardiology 1, 2 (1996), 151--181.Google ScholarCross Ref
- Alban Maxhuni, Angélica Muñoz-Meléndez, Venet Osmani, Humberto Perez, Oscar Mayora, and Eduardo F Morales. 2016. Classification of bipolar disorder episodes based on analysis of voice and motor activity of patients. Pervasive and Mobile Computing (2016). Google ScholarDigital Library
- Charles E McCulloch and John M Neuhaus. 2001. Generalized linear mixed models. Wiley Online Library.Google Scholar
- Abhinav Mehrotra, Robert Hendley, and Mirco Musolesi. 2016. Towards multi-modal anticipatory monitoring of depressive states through the analysis of human-smartphone interaction. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct. ACM, 1132--1138. Google ScholarDigital Library
- Microsoft. 2016. Microsoft Band. (2016). https://www.microsoft.com/microsoft-band/en-us.Google Scholar
- Megan A Moreno, Lauren A Jelenchick, Katie G Egan, Elizabeth Cox, Henry Young, Kerry E Gannon, and Tara Becker. 2011. Feeling bad on Facebook: Depression disclosures by college students on a social networking site. Depression and anxiety 28, 6 (2011), 447--455.Google Scholar
- Christopher JL Murray, Jerry Abraham, Mohammed K Ali, Miriam Alvarado, Charles Atkinson, Larry M Baddour, David H Bartels, Emelia J Benjamin, Kavi Bhalla, Gretchen Birbeck, et al. 2013. The state of US health, 1990--2010: burden of diseases, injuries, and risk factors. JAMA 310, 6 (2013), 591--606.Google ScholarCross Ref
- Christopher JL Murray, Theo Vos, Rafael Lozano, Mohsen Naghavi, Abraham D Flaxman, Catherine Michaud, Majid Ezzati, Kenji Shibuya, Joshua A Salomon, Safa Abdalla, et al. 2013. Disability-adjusted life years (DALYs) for 291 diseases and injuries in 21 regions, 1990--2010: a systematic analysis for the Global Burden of Disease Study 2010. The lancet 380, 9859 (2013), 2197--2223.Google Scholar
- Venet Osmani. 2015. Smartphones in mental health: detecting depressive and manic episodes. IEEE Pervasive Computing 14, 3 (2015), 10--13.Google ScholarDigital Library
- Venet Osmani, Alban Maxhuni, Agnes Grünerbl, Paul Lukowicz, Christian Haring, and Oscar Mayora. 2013. Monitoring activity of patients with bipolar disorder using smart phones. In Proceedings of International Conference on Advances in Mobile Computing 8 Multimedia. ACM, 85. Google ScholarDigital Library
- Skyler Place, Danielle Blanch-Hartigan, Channah Rubin, Cristina Gorrostieta, Caroline Mead, John Kane, Brian P Marx, Joshua Feast, Thilo Deckersbach, et al. 2017. Behavioral Indicators on a Mobile Sensing Platform Predict Clinically Validated Psychiatric Symptoms of Mood and Anxiety Disorders. Journal of Medical Internet Research 19, 3 (2017).Google ScholarCross Ref
- Mashfiqui Rabbi, Shahid Ali, Tanzeem Choudhury, and Ethan Berke. 2011. Passive and in-situ assessment of mental and physical well-being using mobile sensors. In Proceedings of the 13th international conference on Ubiquitous computing. ACM, 385--394. Google ScholarDigital Library
- Matthia Sabatelli, Venet Osmani, Oscar Mayora, Agnes Gruenerbl, and Paul Lukowicz. 2014. Correlation of significant places with self-reported state of bipolar disorder patients. In Wireless Mobile Communication and Healthcare (Mobihealth), 2014 EAI 4th International Conference on. IEEE, 116--119.Google ScholarCross Ref
- Sohrab Saeb, Emily G Lattie, Stephen M Schueller, Konrad P Kording, and David C Mohr. 2016. The relationship between mobile phone location sensor data and depressive symptom severity. Peer J 4 (2016), e2537.Google ScholarCross Ref
- Sohrab Saeb, Mi Zhang, Christopher J Karr, Stephen M Schueller, Marya E Corden, Konrad P Kording, and David C Mohr. 2015. Mobile phone sensor correlates of depressive symptom severity in daily-life behavior: an exploratory study. Journal of medical Internet research 17, 7 (2015).Google ScholarCross Ref
- SAMHSA. 2015. Key Substance Use and Mental Health Indicators in the United States: Results from the 2015 National Survey on Drug Use and Health. (2015). https://www.samhsa.gov/data/sites/default/files/NSDUH-FFR1-2015/NSDUH-FFR1-2015/NSDUH-FFR1-2015.htm.Google Scholar
- Henry Scheffe. 1999. The analysis of variance. Vol. 72. John Wiley 8 Sons.Google Scholar
- Suzanne C Segerstrom and Lise Solberg Nes. 2007. Heart rate variability reflects self-regulatory strength, effort, and fatigue. Psychological science 18, 3 (2007), 275--281.Google Scholar
- John Shawe-Taylor and Nello Cristianini. 2004. Kernel Methods for Pattern Analysis. Cambridge university press. Google ScholarDigital Library
- Robert L Spitzer, Kurt Kroenke, Janet BW Williams, Patient Health Questionnaire Primary Care Study Group, et al. 1999. Validation and utility of a self-report version of PRIME-MD: the PHQ primary care study. Jama 282, 18 (1999), 1737--1744.Google ScholarCross Ref
- Yoshihiko Suhara, Yinzhan Xu, and Alex'Sandy' Pentland. 2017. DeepMood: Forecasting Depressed Mood Based on Self-Reported Histories via Recurrent Neural Networks. In Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 715--724. Google ScholarDigital Library
- Robert Tibshirani. 1996. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society. Series B (Methodological) (1996), 267--288.Google Scholar
- Fani Tsapeli and Mirco Musolesi. 2015. Investigating causality in human behavior from smartphone sensor data: a quasi-experimental approach. EPJ Data Science 4, 1 (2015), 24.Google ScholarCross Ref
- Verily. 2017. Tackling Mental Health at Verily. (2017). https://blog.verily.com/2017/05/tackling-mental-health-at-verily.html.Google Scholar
- Theo Vos, Abraham D Flaxman, Mohsen Naghavi, Rafael Lozano, Catherine Michaud, Majid Ezzati, Kenji Shibuya, Joshua A Salomon, Safa Abdalla, Victor Aboyans, et al. 2013. Years lived with disability (YLDs) for 1160 sequelae of 289 diseases and injuries 1990--2010: a systematic analysis for the Global Burden of Disease Study 2010. The Lancet 380, 9859 (2013), 2163--2196.Google Scholar
- Fabian Wahle, Tobias Kowatsch, Elgar Fleisch, Michael Rufer, and Steffi Weidt. 2016. Mobile sensing and support for people with depression: a pilot trial in the wild. JMIR mHealth and uHealth 4, 3 (2016).Google Scholar
- Rui Wang, Min S. H. Aung, Saeed Abdullah, Rachel Brian, Andrew T. Campbell, Tanzeem Choudhury, Marta Hauser, John Kane, Michael Merrill, Emily A. Scherer, Vincent W. S. Tseng, and Dror Ben-Zeev. 2016. Crosscheck: Toward Passive Sensing and Detection of Mental Health Changes in People with Schizophrenia. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '16). ACM, New York, NY, USA, 886--897. Google ScholarDigital Library
- Rui Wang, Fanglin Chen, Zhenyu Chen, Tianxing Li, Gabriella Harari, Stefanie Tignor, Xia Zhou, Dror Ben-Zeev, and Andrew T. Campbell. 2014. StudentLife: Assessing Mental Health, Academic Performance and Behavioral Trends of College Students Using Smartphones. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '14). ACM, New York, NY, USA, 3--14. Google ScholarDigital Library
- Rui Wang, Gabriella Harari, Peilin Hao, Xia Zhou, and Andrew T Campbell. 2015. SmartGPA: how smartphones can assess and predict academic performance of college students. In Proceedings of the 2015 ACM international joint conference on pervasive and ubiquitous computing. ACM, 295--306. Google ScholarDigital Library
- Rachel Yehuda. 2002. Post-traumatic stress disorder. New England journal of medicine 346, 2 (2002), 108--114.Google Scholar
- Yosef Hochberg Yoav Benjamini. 1995. Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing. Journal of the Royal Statistical Society. Series B (Methodological) 57, 1 (1995), 289--300. http://www.jstor.org/stable/2346101Google ScholarCross Ref
Index Terms
- Tracking Depression Dynamics in College Students Using Mobile Phone and Wearable Sensing
Recommendations
Mobile phone addiction levels and negative emotions among Chinese young adults
This study evaluated the mediating role of interpersonal problems in the link between mobile phone addiction levels and negative emotions among mobile phone addicts and possible-mobile phone addicts respectively. The purpose of this study was to address ...
Facebook use, envy, and depression among college students
A survey of 736 college students found that Facebook use can trigger feelings of envy.Feelings of envy were found to predict depression symptoms.The effect of surveillance use of Facebook on depression is mediated by feelings of envy.Surveillance use of ...
Problematic cell phone use, depression, anxiety, and self-regulation: Evidence from a three year longitudinal study from adolescence to emerging adulthood
AbstractFor a small percentage of cell phone users, cell phone use becomes problematic or addictive, characterized by excessive time spent on the cell phone, interference with social relationships and responsibilities, and difficulty ...
Highlights- Problematic cell phone use is stable between adolescence and emerging adulthood.
Comments