Monitoring Depression in Bipolar Disorder using Circadian Measures from Smartphone Accelerometers

Current management of bipolar disorder relies on self-reported questionnaires and interviews with clinicians. The development of objective measures of deteriorating mood may also allow for early interventions to take place to avoid transitions into depressive states. The objective of this study was to use acceleration data recorded from smartphones to predict levels of depression in a population of participants diagnosed with bipolar disorder. Data were collected from 52 participants, with a mean of 37 weeks of acceleration data with a corresponding depression score recorded per participant. Time varying hidden Markov models were used to extract weekly features of activity, sleep and circadian rhythms. Personalised regression achieved mean absolute errors of 1.00(0.57) from a possible scale of 0 to 27 and was able to classify depression with an accuracy of 0.84(0.16). The results demonstrate features derived from smartphone accelerometers are able to provide objective markers of depression. Low barriers for uptake exist due to the widespread use of smartphones, with personalised models able to account for differences in the behaviour of individuals and provide accurate predictions of depression.

[1]  Wen-Yen Lin,et al.  Activity Monitoring with a Wrist-Worn, Accelerometer-Based Device , 2018, Micromachines.

[2]  Daniel J. Buysse,et al.  Sleep disturbances and depression: risk relationships for subsequent depression and therapeutic implications , 2008, Dialogues in clinical neuroscience.

[3]  Maarten De Vos,et al.  Detecting Bipolar Depression From Geographic Location Data , 2016, IEEE Transactions on Biomedical Engineering.

[4]  M De Vos,et al.  Variability in phase and amplitude of diurnal rhythms is related to variation of mood in bipolar and borderline personality disorder , 2018, Scientific Reports.

[5]  Chelsea Dobbins,et al.  Towards Clustering of Mobile and Smartwatch Accelerometer Data for Physical Activity Recognition , 2018, Informatics.

[6]  Guy M. Goodwin,et al.  Desynchronization of diurnal rhythms in bipolar disorder and borderline personality disorder , 2018, Translational Psychiatry.

[7]  C. Lindgren,et al.  GWAS identifies 14 loci for device-measured physical activity and sleep duration , 2018, Nature Communications.

[8]  Stephan Heckers,et al.  The Value of Psychiatric Diagnoses. , 2015, JAMA psychiatry.

[9]  Willem A. Nolen,et al.  Can Variation in Hypothalamic-Pituitary-Adrenal (HPA)-Axis Activity Explain the Relationship between Depression and Cognition in Bipolar Patients? , 2012, PloS one.

[10]  Oscar Mayora-Ibarra,et al.  Using smart phone mobility traces for the diagnosis of depressive and manic episodes in bipolar patients , 2014, AH.

[11]  Enrico Smeraldi,et al.  Actimetric evidence that CLOCK 3111 T/C SNP influences sleep and activity patterns in patients affected by bipolar depression , 2007, American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics.

[12]  R. Baldessarini,et al.  Circadian activity rhythm abnormalities in ill and recovered bipolar I disorder patients. , 2008, Bipolar disorders.

[13]  Carol A Tamminga,et al.  The relationship between affective state and the rhythmicity of activity in bipolar disorder. , 2014, The Journal of clinical psychiatry.

[14]  Qi Huang,et al.  Hidden Markov models for monitoring circadian rhythmicity in telemetric activity data , 2018, Journal of The Royal Society Interface.

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

[16]  P. Lukowicz,et al.  Towards smart phone based monitoring of bipolar disorder , 2012, mHealthSys '12.

[17]  R. Kessler,et al.  Prevalence, severity, and unmet need for treatment of mental disorders in the World Health Organization World Mental Health Surveys. , 2004, JAMA.

[18]  M. Bauer,et al.  Smartphone-based objective monitoring in bipolar disorder: status and considerations , 2018, International Journal of Bipolar Disorders.

[19]  A I Pack,et al.  Estimating sleep parameters using an accelerometer without sleep diary , 2018, Scientific Reports.

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

[21]  A. Feigl,et al.  The Global Economic Burden of Noncommunicable Diseases , 2012 .

[22]  T. Roth,et al.  Sleep disturbance and psychiatric disorders: A longitudinal epidemiological study of young Adults , 1996, Biological Psychiatry.

[23]  Oscar Mayora-Ibarra,et al.  Smartphone-Based Recognition of States and State Changes in Bipolar Disorder Patients , 2015, IEEE Journal of Biomedical and Health Informatics.

[24]  Luca Citi,et al.  Characterization of Depressive States in Bipolar Patients Using Wearable Textile Technology and Instantaneous Heart Rate Variability Assessment , 2015, IEEE Journal of Biomedical and Health Informatics.

[25]  D J Kupfer,et al.  Self-reported sleep disturbance as a prodromal symptom in recurrent depression. , 1997, Journal of affective disorders.

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

[27]  H. Lôo.  [On bipolar disorder]. , 2008, L'Encephale.

[28]  E. Walker,et al.  Diagnostic and Statistical Manual of Mental Disorders , 2013 .

[29]  Ole Bernt Fasmer,et al.  Actigraphic Assessment of Motor Activity in Acutely Admitted Inpatients with Bipolar Disorder , 2014, PloS one.

[30]  J. Prasko,et al.  The circadian system of patients with bipolar disorder differs in episodes of mania and depression , 2015, Bipolar disorders.

[31]  Joseph Firth,et al.  Sedentary behavior and physical activity levels in people with schizophrenia, bipolar disorder and major depressive disorder: a global systematic review and meta‐analysis , 2017, World psychiatry : official journal of the World Psychiatric Association.

[32]  G. Clifford,et al.  Daily longitudinal self-monitoring of mood variability in bipolar disorder and borderline personality disorder , 2016, Journal of affective disorders.

[33]  John A. Stankovic,et al.  Empath: a continuous remote emotional health monitoring system for depressive illness , 2011, Wireless Health.

[34]  Athanasios Tsanas,et al.  Clinical Insight Into Latent Variables of Psychiatric Questionnaires for Mood Symptom Self-Assessment , 2017, JMIR mental health.

[35]  M. Speekenbrink,et al.  depmixS4: An R Package for Hidden Markov Models , 2010 .

[36]  P. F. D. de Bruin,et al.  Chronotype and circadian rhythm in bipolar disorder: A systematic review. , 2017, Sleep medicine reviews.

[37]  C. Morin,et al.  Self-reported sleep and mood disturbance in chronic pain patients. , 1998, The Clinical journal of pain.

[38]  G. Clifford,et al.  A multi-sensor monitoring system for objective mental health management in resource constrained environments , 2014 .

[39]  M. de Vos,et al.  Group-Personalized Regression Models for Predicting Mental Health Scores From Objective Mobile Phone Data Streams: Observational Study , 2018, Journal of medical Internet research.

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

[41]  J. Markowitz,et al.  The 16-Item quick inventory of depressive symptomatology (QIDS), clinician rating (QIDS-C), and self-report (QIDS-SR): a psychometric evaluation in patients with chronic major depression , 2003, Biological Psychiatry.