ABSTRACT
Suicide is the second leading cause of death among young adults but the challenges of preventing suicide are significant because the signs often seem invisible. Research has shown that clinicians are not able to reliably predict when someone is at greatest risk. In this paper, we describe the design, collection, and analysis of text messages from individuals with a history of suicidal thoughts and behaviors to build a model to identify periods of suicidality (i.e., suicidal ideation and non-fatal suicide attempts). By reconstructing the timeline of recent suicidal behaviors through a retrospective clinical interview, this study utilizes a prospective research design to understand if text communications can predict periods of suicidality versus depression. Identifying subtle clues in communication indicating when someone is at heightened risk of a suicide attempt may allow for more effective prevention of suicide.
Supplemental Material
- Yuval Barak-Corren, Victor M. Castro, Solomon Javitt, Alison G. Hoffnagle, Yael Dai, Roy H. Perlis, Matthew K. Nock, Jordan W. Smoller, and Ben Y. Reis. 2017. Predicting Suicidal Behavior From Longitudinal Electronic Health Records. Am J Psychiatry 174, 2 (Feb 2017), 154--162.Google ScholarCross Ref
- George W Blair-West, Chris H Cantor, Graham W Mellsop, and Margo L Eyeson-Annan. 1999. Lifetime suicide risk in major depression: sex and age determinants. J Affect Disord 55, 2 (Oct 1999), 171--178.Google ScholarCross Ref
- Scott R Braithwaite, Christophe Giraud-Carrier, Josh West, Michael D Barnes, and Carl Lee Hanson. 2016. Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality. JMIR Ment Health 3, 2 (May 2016), e21.Google ScholarCross Ref
- Katie A Busch, Jan Fawcett, and Douglas G Jacobs. 2003. Clinical correlates of inpatient suicide. J Clin Psychiatry 64, 1 (Jan 2003), 14--19.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 (UbiComp '15). ACM, New York, NY, USA, 1293--1304. Google ScholarDigital Library
- Jonathan T. Cavanagh, Alan J. Carson, Michael Sharpe, and Stephen M. Lawrie. 2003. Psychological autopsy studies of suicide: A systematic review. Psychol Med 33, 3 (Apr 2003), 395--405.Google ScholarCross Ref
- François et al. Chollet. 2015. Keras. https://github.com/fchollet/keras. (2015).Google Scholar
- Benjamin L. Cook, Ana M. Progovac, Pei Chen, Brian Mullin, Sherry Hou, and Enrique Baca-Garcia. 2016. Novel Use of Natural Language Processing (NLP) to Predict Suicidal Ideation and Psychiatric Symptoms in a Text-Based Mental Health Intervention in Madrid. Comput Math Methods Med 2016 (Sep 2016), 1--8.Google Scholar
- Munmun De Choudhury, Emre Kiciman, Mark Dredze, Glen Coppersmith, and Mrinal Kumar. 2016. Discovering Shifts to Suicidal Ideation from Mental Health Content in Social Media. In Proceedings of the 2016 SIGCHI Conference on Human Factors in Computing Systems (CHI '16). ACM, New York, NY, USA, 2098--2110. Google ScholarDigital Library
- Emory University. 2017. Emory Cares 4 U: Suicide Statistics. (2017). Retrieved October 24, 2016 from http://www.emorycaresforyou.emory.edu/resources/ suicidestatistics.html.Google Scholar
- U.S. Centers for Disease Control and Prevention. 2014. Web-based Injury Statistics Query and Reporting System (WISQARS). (2014). Retrieved March 31, 2014 from http://www.cdc.gov/injury/wisqars.Google Scholar
- Joseph C. Franklin, Jessica D. Ribeiro, Kathryn R. Fox, Kate H. Bentley, Evan M. Kleiman, Xieyining Huang, Katherine M. Musacchio, Adam C. Jaroszewski, Bernard P. Chang, and Matthew K. Nock. 2017. Risk factors for suicidal thoughts and behaviors: A meta-analysis of 50 years of research. Psychol Bull 43, 2 (Feb 2017), 187--232.Google Scholar
- Yusong Gao, Ang Li, Tingshao Zhu, Xiaoqian Liu, and Xingyun Liu. 2016. How smartphone usage correlates with social anxiety and loneliness. PeerJ 4 (Jul 2016), e2197.Google Scholar
- Madelyn S Gould, Frank A Marrocco, Marjorie Kleinman, John Graham Thomas, Katherine Mostkoff, Jean Cote, and Mark Davies. 2005. Evaluating Iatrogenic Risk of Youth Suicide Screening Programs: A Randomized Controlled Trial. JAMA 293, 13 (Apr 2005), 1635--43.Google Scholar
- Yu Huang, Jiaqi Gong, Mark Rucker, Philip Chow, Karl Fua, Matthew S. Gerber, Bethany Teachman, and Laura E. Barnes. 2017. Discovery of Behavioral Markers of Social Anxiety from Smartphone Sensor Data. In Proceedings of the 1st Workshop on Digital Biomarkers (Digital Biomarkers '17). ACM, New York, NY, USA, 9--14. Google ScholarDigital Library
- Yu Huang, Haoyi Xiong, Kevin Leach, Yuyan Zhang, Philip Chow, Karl Fua, Bethany A Teachman, and Laura E Barnes. 2016. Assessing social anxiety using gps trajectories and point-of-interest data. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '16). ACM, New York, NY, USA, 898--903. Google ScholarDigital Library
- Institutional Review Board for Social and Behavioral Sciences at University of Virginia. 2014. Psychology Pool. (2014). http://www.virginia.edu/vpr/irb/sbs/ resources{_}guide{_}pools{_}existing{_}psych.html.Google Scholar
- ET Isometsä. 2001. Psychological autopsy studies -- a review. Eur Psychiatry 16, 7 (Nov 2001), 379--385.Google ScholarCross Ref
- Sachin H Jain, Brian W Powers, Jared B Hawkins, and John S Brownstein. 2015. The digital phenotype. Nat Biotechnol 33, 5 (May 2015), 462--463.Google ScholarCross Ref
- Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980 (2014). Retrieved from https://arxiv.org/abs/1412.6980.Google Scholar
- Kamran Kowsari, Donald E Brown, Mojtaba Heidarysafa, Kiana Jafari Meimandi,, Matthew S Gerber, and Laura E Barnes. 2017. HDLTex: Hierarchical Deep Learning for Text Classification. In Machine Learning and Applications (ICMLA), 2017 16th IEEE International Conference on. IEEE.Google ScholarCross Ref
- Neal Lathia, Veljko Pejovic, Kiran K Rachuri, Cecilia Mascolo, Mirco Musolesi, and Peter J Rentfrow. 2013. Smartphones for large-scale behavior change interventions. IEEE Pervasive Computing 12, 3 (2013), 66--73. Google ScholarDigital Library
- J John Mann, Ann Haas, Lars Mehlum, and Michael Phillips. 2005. Suicide Prevention Strategies. JAMA 294, 16 (Oct 2005), 2064--2074.Google ScholarCross Ref
- Mauri J Marttunen, Hillevi M Aro, and Jouko K Lönnqvist. 1993. Adolescence and suicide: A review of psychological autopsy studies. Eur Child Adolesc Psychiatry 2, 1 (Jan 1993), 10--18.Google ScholarCross Ref
- Alexis M. May and E. David Klonsky. 2016. What Distinguishes Suicide Attempters From Suicide Ideators? A Meta-Analysis of Potential Factors. Clin Psychol--Sci Pr 23, 1 (Mar 2016), 5--20.Google ScholarCross Ref
- Alexander J Millner, Michael D Lee, and Matthew K Nock. 2017. Describing and Measuring the Pathway to Suicide Attempts: A Preliminary Study. Suicide Life Threat Behav 47, 3 (Jun 2017), 353--369.Google ScholarCross Ref
- Jerome A. Motto and Alan G. Bostrom. 2001. A Randomized Controlled Trial of Postcrisis Suicide Prevention. Psychiatr Serv 52, 6 (Jun 2001), 828--833.Google ScholarCross Ref
- Jinseok Nam, Jungi Kim, Eneldo Loza Mencía, Iryna Gurevych, and Johannes Fürnkranz. 2014. Large-scale multi-label text classification -- revisiting neural networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2014). Springer Berlin Heidelberg, Berlin, Heidelberg, 437--452. Google ScholarDigital Library
- Matthew K. Nock, Guilherme Borges, Evelyn J. Bromet, Christine B. Cha, Ronald C. Kessler, and Sing Lee. 2008. Suicide and Suicidal Behavior. Epidemiol Rev 30, 1 (July 2008), 133--154.Google ScholarCross Ref
- M. K. Nock, A. J. Millner, C. A. Deming, and C. R. Glenn. 2014. Depression and suicide (3rd ed.). The Guilford Press, New York, NY, Chapter 24, 448--467.Google Scholar
- Matthew K Nock, Jennifer M Park, Christine T Finn, Tara L Deliberto, Halina J Dour, and Mahzarin R Banaji. 2010. Measuring the suicidal mind: implicit cognition predicts suicidal behavior. Psychol Sci 21, 4 (Apr 2010), 511--517.Google ScholarCross Ref
- OurDataHelps. 2016. OurDataHelps.org: The world needs more Data Donors. (2016). Retrieved from ourdatahelps.org.Google Scholar
- Michael J. Paul and Mark Dredze. 2017. Social Monitoring for Public Health. Synthesis Lectures on Information Concepts, Retrieval, and Services 9, 5 (Aug 2017), 1--183. Google ScholarDigital Library
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine Learning in Python. J Mach Learn Res 12 (2011), 2825--2830. Google ScholarDigital Library
- J.W. Pennebaker, R.J. Booth, R.L. Boyd, and M.E. Francis. 2015. Linguistic Inquiry and Word Count: LIWC2015. Austin, TX: Pennebaker Conglomerates (www.LIWC.net). (2015).Google Scholar
- John Pestian, Henry Nasrallah, Pawel Matykiewicz, Aurora Bennett, and Antoon Leenaars. 2010. Suicide Note Classification Using Natural Language Processing: A Content Analysis. Biomed Inform Insights 2010, 3 (Aug 2010), 19--28. http://www.ncbi.nlm.nih.gov/pubmed/21643548Google Scholar
- John P. Pestian, Jacqueline Grupp-Phelan, Kevin Bretonnel Cohen, Gabriel Meyers, Linda A. Richey, Pawel Matykiewicz, and Michael T. Sorter. 2016. A Controlled Trial Using Natural Language Processing to Examine the Language of Suicidal Adolescents in the Emergency Department. Suicide Life Threat Behav 46, 2 (Apr 2016), 154--159.Google ScholarCross Ref
- Chris Poulin, Brian Shiner, Paul Thompson, Linas Vepstas, Yinong Young-Xu, Benjamin Goertzel, Bradley Watts, Laura Flashman, and Thomas McAllister. 2014. Predicting the Risk of Suicide by Analyzing the Text of Clinical Notes. PLoS One 9, 1 (Jan 2014), e85733.Google ScholarCross Ref
- Jacob Poushter. 2016. Smartphone Ownership and Internet Usage Continues to Climb in Emerging Economies. Pew Research Center, Washington, D.C.Google Scholar
- Ping Qin and Merete Nordentoft. 2005. Suicide risk in relation to psychiatric hospitalization: evidence based on longitudinal registers. Arch Gen Psychiatry 62, 4 (Apr 2005), 427--432.Google ScholarCross Ref
- Sarah K Reynolds, Noam Lindenboim, Katherine Anne Comtois, Angela Murray, and Marsha M Linehan. 2006. Risky Assessments: Participant Suicidality and Distress Associated with Research Assessments in a Treatment Study of Suicidal Behavior. Suicide Life Threat Behav 36, 1 (Feb 2006), 19--34.Google ScholarCross Ref
- M. David Rudd. 2015. Core competencies, warning signs, and a framework for suicide risk assessment in clinical practice. The Oxford Handbook of Suicide and Self-Injury. J Clin Psychol 76 (2015), 323--352. Issue E896.Google Scholar
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. J Mach Learn Res 15 (Jun 2014), 1929--1958. Google ScholarDigital Library
- Sabrina Tavernise. 2016. U.S. Suicide Rate Surges to a 30-Year High. (2016). Retrieved from http://www.nytimes.com/2016/04/22/health/us-suiciderate-surges-to-a-30-year-high.html.Google Scholar
- U.S. Centers for Disease Control and Prevention: National Center for Health Statistics. 2016. Leading Causes of Death. (2016). Retrieved October 24, 2016 from http: //www.cdc.gov/nchs/fastats/leading-causes-of-death.htm.Google Scholar
- M Valenstein, D Eisenberg, JF McCarthy, KL Austin, D Ganoczy, HM Kim, K Zivin, JD Piette, M Olfson, and FC Blow. 2009. Service implications of providing intensive monitoring during high-risk periods for suicide among VA patients with depression. Psychiatr Serv 60, 4 (Apr 2009), 439--44.Google ScholarCross Ref
- Colin G. Walsh, Jessica D. Ribeiro, and Joseph C. Franklin. 2017. Predicting Risk of Suicide Attempts Over Time Through Machine Learning. Clin Psychol Sci 5, 3 (Apr 2017), 457--469.Google ScholarCross Ref
- David L. Williams, Victoria L. Crittenden, Teeda Keo, and Paulette McCarty. 2012. The use of social media: an exploratory study of usage among digital natives. J Publ Aff 12, 2 (May 2012), 127--136.Google ScholarCross Ref
- Haoyi Xiong, Jinghe Zhang, Yu Huang, Kevin Leach, and Laura E. Barnes. 2017. Daehr: A Discriminant Analysis Framework for Electronic Health Record Data and an Application to Early Detection of Mental Health Disorders. ACM Trans. Intell. Syst. Technol. 8, 3, Article 47 (Feb 2017), 21 pages. Google ScholarDigital Library
- Jinghe Zhang, Haoyi Xiong, Yu Huang, Hao Wu, Kevin Leach, and Laura E Barnes. 2015. MSEQ: Early Detection of Anxiety and Depression via Temporal Orders of Diagnoses in Electronic Health Data. In 2015 IEEE International Conference on Big Data (Big Data 2015). 2569--2577. Google ScholarDigital Library
Index Terms
- Identification of Imminent Suicide Risk Among Young Adults using Text Messages
Recommendations
Knowledge-aware Assessment of Severity of Suicide Risk for Early Intervention
WWW '19: The World Wide Web ConferenceMental health illness such as depression is a significant risk factor for suicide ideation, behaviors, and attempts. A report by Substance Abuse and Mental Health Services Administration (SAMHSA) shows that 80% of the patients suffering from Borderline ...
Use of Text Search to Effectively Identify Lifetime Prevalence of Suicide Attempts among Veterans
HICSS '13: Proceedings of the 2013 46th Hawaii International Conference on System SciencesSuicide is an important emerging problem among active duty personnel and veterans of recent conflicts in Iraq and Afghanistan. Suicide rates among veterans treated in the VA System are about 50% higher than in the general population, and the rate of ...
Cloud based mental state monitoring system for suicide risk reconnaissance using wearable bio-sensors
ICUIMC '14: Proceedings of the 8th International Conference on Ubiquitous Information Management and CommunicationDevelopment of wireless body- and bio-sensor network opens a new horizon of healthcare especially to measure the vital physical signs of personnel for disease diagnosis and patient monitoring. And the cloud computing technology has enabled patient ...
Comments