Predicting Symptom Trajectories of Schizophrenia using Mobile Sensing

Continuously monitoring schizophrenia patients’ psychiatric symptoms is crucial for in-time intervention and treatment adjustment. The Brief Psychiatric Rating Scale (BPRS) is a survey administered by clinicians to evaluate symptom severity in schizophrenia. The CrossCheck symptom prediction system is capable of tracking schizophrenia symptoms based on BPRS using passive sensing from mobile phones. We present results from an ongoing randomized control trial, where passive sensing data, self-reports, and clinician administered 7-item BPRS surveys are collected from 36 outpatients with schizophrenia recently discharged from hospital over a period ranging from 2-12 months. We show that our system can predict a symptom scale score based on a 7-item BPRS within ±1.45 error on average using automatically tracked behavioral features from phones (e.g., mobility, conversation, activity, smartphone usage, the ambient acoustic environment) and user supplied self-reports. Importantly, we show our system is also capable of predicting an individual BPRS score within ±1.59 error purely based on passive sensing from phones without any self-reported information from outpatients. Finally, we discuss how well our predictive system reflects symptoms experienced by patients by reviewing a number of case studies.

[1]  Jeff A. Bilmes,et al.  A Privacy-Sensitive Approach to Modeling Multi-Person Conversations , 2007, IJCAI.

[2]  E. LESTER SMITH,et al.  AND OTHERS , 2005 .

[3]  D. Ben-Zeev,et al.  Comparing retrospective reports to real-time/real-place mobile assessments in individuals with schizophrenia and a nonclinical comparison group. , 2012, Schizophrenia bulletin.

[4]  R. Liberman,et al.  Brief Psychiatric Rating Scale (BPRS) Expanded Version (4.0): Scales, Anchor Points, and Administration Manual , 1993 .

[5]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[6]  Akram Alomainy,et al.  Large scale mood and stress self-assessments on a smartwatch , 2016, UbiComp Adjunct.

[7]  Alexander Russell,et al.  Behavior vs. introspection: refining prediction of clinical depression via smartphone sensing data , 2016, 2016 IEEE Wireless Health (WH).

[8]  S. Zeger,et al.  Longitudinal data analysis using generalized linear models , 1986 .

[9]  Mirco Musolesi,et al.  Towards multi-modal anticipatory monitoring of depressive states through the analysis of human-smartphone interaction , 2016, UbiComp Adjunct.

[10]  E. Echeburúa,et al.  Prediction of Relapse After Cognitive-Behavioral Treatment of Gambling Disorder in Individuals With Chronic Schizophrenia: A Survival Analysis. , 2017, Behavior therapy.

[11]  Emre Ertin,et al.  cStress: towards a gold standard for continuous stress assessment in the mobile environment , 2015, UbiComp.

[12]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[13]  M. Birchwood,et al.  Predicting relapse in schizophrenia: the development and implementation of an early signs monitoring system using patients and families as observers, a preliminary investigation , 1989, Psychological Medicine.

[14]  C. Martin.  2015 , 2015, Les 25 ans de l’OMC: Une rétrospective en photos.

[15]  J. Overall,et al.  The Brief Psychiatric Rating Scale , 1962 .

[16]  P. Diggle.  Analysis of Longitudinal Data , 1995 .

[17]  Andrew T. Campbell,et al.  Mobile Behavioral Sensing for Outpatients and Inpatients With Schizophrenia. , 2016, Psychiatric services.

[18]  Akane Sano,et al.  Stress Recognition Using Wearable Sensors and Mobile Phones , 2013, 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction.

[19]  T C Chalmers,et al.  A method for assessing the quality of a randomized control trial. , 1981, Controlled clinical trials.

[20]  K Y Liang,et al.  An overview of methods for the analysis of longitudinal data. , 1992, Statistics in medicine.

[21]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[22]  R. Spitzer,et al.  Validation and utility of a self-report version of PRIME-MD: the PHQ primary care study. Primary Care Evaluation of Mental Disorders. Patient Health Questionnaire. , 1999, JAMA.

[23]  G. Strauss,et al.  Periods of recovery in deficit syndrome schizophrenia: a 20-year multi-follow-up longitudinal study. , 2010, Schizophrenia bulletin.

[24]  Jeff A. Bilmes,et al.  Conversation detection and speaker segmentation in privacy-sensitive situated speech data , 2007, INTERSPEECH.

[25]  J Elith,et al.  A working guide to boosted regression trees. , 2008, The Journal of animal ecology.

[26]  Konrad Paul Kording,et al.  Mobile Phone Sensor Correlates of Depressive Symptom Severity in Daily-Life Behavior: An Exploratory Study , 2015, Journal of medical Internet research.

[27]  Andrew T. Campbell,et al.  Bewell: A smartphone application to monitor, model and promote wellbeing , 2011, PervasiveHealth 2011.

[28]  John W. Haller,et al.  Lateralized attentional abnormality in schizophrenia is correlated with severity of symptoms , 1993, Biological Psychiatry.

[29]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[30]  Oscar Mayora-Ibarra,et al.  Monitoring activity of patients with bipolar disorder using smart phones , 2013, MoMM '13.

[31]  R. Spitzer,et al.  The PHQ-9 , 2001, Journal of General Internal Medicine.

[32]  Yutaka Arakawa,et al.  COSMS: unconscious stress monitoring system for office worker , 2016, UbiComp Adjunct.

[33]  Matjaz Gams,et al.  Continuous stress detection using a wrist device: in laboratory and real life , 2016, UbiComp Adjunct.

[34]  Gary J. Robertson,et al.  Wide‐Range Achievement Test , 2010 .

[35]  Oscar Mayora-Ibarra,et al.  Correlation of significant places with self-reported state of bipolar disorder patients , 2014, 2014 4th International Conference on Wireless Mobile Communication and Healthcare - Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH).

[36]  Fanglin Chen,et al.  StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones , 2014, UbiComp.

[37]  Daniel Gatica-Perez,et al.  StressSense: detecting stress in unconstrained acoustic environments using smartphones , 2012, UbiComp.

[38]  J. Sweeney,et al.  Drug abuse in schizophrenic patients: clinical correlates and reasons for use. , 1991, The American journal of psychiatry.

[39]  Melissa P. DelBello,et al.  Early response or nonresponse at week 2 and week 3 predict ultimate response or nonresponse in adolescents with schizophrenia treated with olanzapine: results from a 6-week randomized, placebo-controlled trial , 2015, European Child & Adolescent Psychiatry.

[40]  Vincent W. S. Tseng,et al.  CrossCheck: Integrating Self-Report, Behavioral Sensing, and Smartphone Use to Identify Digital Indicators of Psychotic Relapse , 2017, Psychiatric rehabilitation journal.

[41]  Tanzeem Choudhury,et al.  Automatic detection of social rhythms in bipolar disorder , 2016, J. Am. Medical Informatics Assoc..

[42]  Henry A. Kautz,et al.  Capturing Spontaneous Conversation and Social Dynamics: A Privacy-Sensitive Data Collection Effort , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[43]  Inbal Nahum-Shani,et al.  Visualization of time-series sensor data to inform the design of just-in-time adaptive stress interventions , 2015, UbiComp.

[44]  Fanglin Chen,et al.  Unobtrusive sleep monitoring using smartphones , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[45]  Deborah Estrin,et al.  Leveraging Multi-Modal Sensing for Mobile Health: A Case Review in Chronic Pain , 2016, IEEE Journal of Selected Topics in Signal Processing.

[46]  Paul Lukowicz,et al.  Can smartphones detect stress-related changes in the behaviour of individuals? , 2012, 2012 IEEE International Conference on Pervasive Computing and Communications Workshops.

[47]  Oscar Mayora-Ibarra,et al.  Classification of bipolar disorder episodes based on analysis of voice and motor activity of patients , 2016, Pervasive Mob. Comput..

[48]  Mirco Musolesi,et al.  Trajectories of depression: unobtrusive monitoring of depressive states by means of smartphone mobility traces analysis , 2015, UbiComp.

[49]  Helen Koo,et al.  Stresssense: skin conductivity monitoring garment with a mobile app , 2016, UbiComp Adjunct.

[50]  Emiliano Miluzzo,et al.  A survey of mobile phone sensing , 2010, IEEE Communications Magazine.

[51]  Lawrence B. Inderbitzin,et al.  Substance use: a powerful predictor of relapse in schizophrenia , 1996, Schizophrenia Research.

[52]  Venet Osmani,et al.  Smartphones in Mental Health: Detecting Depressive and Manic Episodes , 2015, IEEE Pervasive Computing.

[53]  John E. Overall,et al.  The Brief Psychiatric Rating Scale , 1962 .

[54]  R. Spitzer,et al.  The PHQ-9: A new depression diagnostic and severity measure , 2002 .

[55]  Tanzeem Choudhury,et al.  Passive and In-Situ assessment of mental and physical well-being using mobile sensors , 2011, UbiComp '11.

[56]  Frederick R. Forst,et al.  On robust estimation of the location parameter , 1980 .

[57]  Gernot Bahle,et al.  Utilizing Smartphones as an Effective Way to Support Patients with Bipolar Disorder: Results of the Monarca Study , 2015, European Psychiatry.

[58]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[59]  Rui Wang,et al.  CrossCheck: toward passive sensing and detection of mental health changes in people with schizophrenia , 2016, UbiComp.

[60]  Alex Pentland,et al.  Daily Stress Recognition from Mobile Phone Data, Weather Conditions and Individual Traits , 2014, ACM Multimedia.

[61]  Yu Huang,et al.  DEMONS: an integrated framework for examining associations between physiology and self-reported affect tied to depressive symptoms , 2016, UbiComp Adjunct.

[62]  Konrad Paul Kording,et al.  The relationship between mobile phone location sensor data and depressive symptom severity , 2016, PeerJ.

[63]  Maximilian Kerz,et al.  SleepSight: a wearables-based relapse prevention system for schizophrenia , 2015, UbiComp Adjunct.

[64]  Gregory A Aarons,et al.  Incarceration among adults who are in the public mental health system: rates, risk factors, and short-term outcomes. , 2012, Psychiatric services.

[65]  R. Liberman,et al.  Consistency of Brief Psychiatric Rating Scale Factor Structure across a Broad Spectrum of Schizophrenia Patients , 2007, Psychopathology.

[66]  Simone Ullrich,et al.  Paranoid Ideation and Violence: Meta-analysis of Individual Subject Data of 7 Population Surveys , 2016, Schizophrenia bulletin.

[67]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[68]  Josep Maria Haro,et al.  Psychotic-Like Experiences and Nonsuidical Self-Injury in England: Results from a National Survey , 2015, PloS one.

[69]  P. Burton,et al.  Extending the simple linear regression model to account for correlated responses: an introduction to generalized estimating equations and multi-level mixed modelling. , 1998, Statistics in medicine.