Abstract
In this paper, we address the problem of predicting schizophrenia based on a persons measured motor activity over time. A key challenge to achieve this is how to extract features from the activity data that can efficiently separate schizophrenia patients from healthy subjects. To achieve this, we suggest to fit time dependent hidden Markov models with and without integrated covariates and letting the estimated model parameters represent our features. To further evaluate the efficiency of these features, we suggest to use them as features in a classification method (logistic regression) to separate schizophrenia patients from healthy subjects. The results show that the estimated hidden Markov model parameters are well-performing in predicting schizophrenia, and outperform features derived from other methods in the literature in terms of goodness-of-fit and classification performance.
Similar content being viewed by others
Data Availibility Statement
The dataset analysed during the current study is available in the Simula Datasets repository [59]
References
World Health Organization (2004) Promoting mental health: concepts, emerging evidence, practice: summary report. World Health Organization, Geneva
Ropper AH, Marder SR, Cannon TD (2019) N Engl J Med 381:1753
NI (2021) of Mental Health, Schizophrenia, NIH Publication No. 21-MH-8082
Gaebel W, Wölwer W (2010) Gesundheitsberichterstattung des bundes heft 50. Rober Koch Institut, Berlin
AP Association et al (2020) Publication manual of the American Psychological Association, (American Psychological Association, 2019)
Garcia-Ceja E, Riegler M, Nordgreen T, Jakobsen P, Oedegaard KJ, Tørresen J (2018) Mental health monitoring with multimodal sensing and machine learning: a survey. Pervasive Mob Comput 51:1
Jakobsen P, Stautland A, Riegler MA, Cote-Allard U, Sepasdar Z, Nordgreen T, Torresen J, Fasmer OB, Oedegaard KJ (2021) Complexity and variability analyses of motor activity distinguish mood states in bipolar disorder, medRxiv
Harvey AG, Murray G, Chandler RA, Soehner A (2011) Sleep disturbance as transdiagnostic: consideration of neurobiological mechanisms. Clin Psychol Rev 31(2):225
Meyer N, Faulkner SM, McCutcheon RA, Pillinger T, Dijk DJ, MacCabe JH (2020) Sleep and circadian rhythm disturbance in remitted schizophrenia and bipolar disorder: a systematic review and meta-analysis. Schizophr Bull. https://doi.org/10.1093/schbul/sbaa024
Dibner C, Schibler U, Albrecht U (2010) The mammalian circadian timing system: organization and coordination of central and peripheral clocks. Annu Rev Physiol 72:517
Delorme TC, Srivastava LK, Cermakian N (2020) Are circadian disturbances a core pathophysiological component of schizophrenia? J Biol Rhythms 35(4):325
Henson P, Barnett I, Keshavan M, Torous J (2020) Towards clinically actionable digital phenoty** targets in schizophrenia. npj Schizophr 6(1):1
Motohashi Y, Maeda A, Wakamatsu H, Higuchi S, Yuasa T (2000) Circadian rhythm abnormalities of wrist activity of institutionalized dependent elderly persons with dementia. J Gerontol Ser A Biol Sci Med Sci 55(12):M740
Komijani H, Parsaei MR, Khajeh E, Golkar MJ, Zarrabi H (2019) Eeg classification using recurrent adaptive neuro-fuzzy network based on time-series prediction. Neural Comput Appl 31(7):2551
Aydin I, Karakose M, Akin E (2020) A new method for time series classification using multi-dimensional phase space and a statistical control chart. Neural Comput Appl 32(11):7439
Abu Arqub O (2017) Adaptation of reproducing kernel algorithm for solving fuzzy Fredholm–Volterra integrodifferential equations. Neural Comput Appl 28(7):1591
Momani S, Abo-Hammour ZS, Alsmadi OM (2016) Solution of inverse kinematics problem using genetic algorithms. Appl Math Inf Sci 10(1):225
Abo-Hammour Z, Abu Arqub O, Momani S, Shawagfeh N (2014) Optimization solution of Troesch’s and Bratu’s problems of ordinary type using novel continuous genetic algorithm. Discrete Dyn Nat Soc. https://doi.org/10.1155/2014/401696
Xu Z, Laber EB, Staicu AM (2020) Hierarchical continuous time hidden Markov model, with application in zero-inflated accelerometer data. In: Zhao Y, Chen DG (eds) Statistical modeling in biomedical research. Springer, Berlin, pp 125–142
Witowski V (2018) Hmmpa-package: analysing accelerometer data using hidden markov models, CRAN R Packages
Huang Q, Cohen D, Komarzynski S, Li XM, Innominato P, Lévi F, Finkenstädt B (2018) Hidden Markov models for monitoring circadian rhythmicity in telemetric activity data. J Royal Soc Interface 15(139):20170885
Carr O, Andreotti F, Saunders KE, Palmius N, Goodwin GM, De Vos M (2020) Monitoring depression in bipolar disorder using circadian measures from smartphone accelerometers, ar**v preprint ar**v:2007.02064
Boeker M, Riegler MA, Hammer HL, Halvorsen P, Fasmer OB, Jakobsen P (2021) In: Proceedings of IEEE international symposium on computer-based medical systems (CBMS) (IEEE, 2021) pp 432–437
Morgenthaler T, Alessi C, Friedman L, Owens J, Kapur V, Boehlecke B, Brown T, Chesson A Jr, Coleman J, Lee-Chiong T et al (2007) Practice parameters for the use of actigraphy in the assessment of sleep and sleep disorders: an update for 2007. Sleep 30(4):519
Sadeh A (2011) The role and validity of actigraphy in sleep medicine: an update. Sleep Med Rev 15(4):259
Ancoli-Israel S, Cole R, Alessi C, Chambers M, Moorcroft W, Pollak CP (2003) The role of actigraphy in the study of sleep and circadian rhythms. Sleep 26(3):342
Tahmasian M, Khazaie H, Golshani S, Avis KT (2013) Clinical application of actigraphy in psychotic disorders: a systematic review. Curr Psychiatry Rep 15(6):359
Afonso P, Figueira ML, Paiva T (2014) Sleep-wake patterns in schizophrenia patients compared to healthy controls. World J Biol Psychiatry 15(7):517
Apiquian R, Fresán A, Muñoz-Delgado J, Kiang M, Ulloa RE, Kapur S (2008) Variations of rest-activity rhythm and sleep-wake in schizophrenic patients versus healthy subjects: an actigraphic comparative study. Biol Rhythm Res 39(1):69
Docx L, Sabbe B, Provinciael P, Merckx N, Morrens M (2013) Quantitative psychomotor dysfunction in schizophrenia: a loss of drive, impaired movement execution or both? Neuropsychobiology 68(4):221
Robillard R, Hermens DF, Naismith SL, White D, Rogers NL, Ip TK, Mullin SJ, Alvares GA, Guastella AJ, Smith KL et al (2015) Ambulatory sleep-wake patterns and variability in young people with emerging mental disorders. J Psychiatry Neurosci JPN 40(1):28
Kume Y, Sugita T, Oga K, Kagami K, Igarashi H (2015) A pilot study: comparative research of social functioning, circadian rhythm parameters, and cognitive function among institutional inpatients, and outpatients with chronic schizophrenia and healthy elderly people. Int Psychogeriatr 27(1):135
Jakobsen P, Garcia-Ceja E, Riegler M, Stabell LA, Nordgreen T, Torresen J, Fasmer OB, Oedegaard KJ (2020) Applying machine learning in motor activity time series of depressed bipolar and unipolar patients compared to healthy controls. Plos one 15(8):e0231995
Hauge ER, Berle JØ, Oedegaard KJ, Holsten F, Fasmer OB (2011) Nonlinear analysis of motor activity shows differences between schizophrenia and depression: a study using fourier analysis and sample entropy. PloS one 6(1):e16291
Krane-Gartiser K, Henriksen TE, Morken G, Vaaler AE, Fasmer OB (2018) Motor activity patterns in acute schizophrenia and other psychotic disorders can be differentiated from bipolar mania and unipolar depression. Psychiatry Res 270:418
Fasmer OB, Hauge E, Berle JØ, Dilsaver S, Oedegaard KJ (2016) Distribution of active and resting periods in the motor activity of patients with depression and schizophrenia. Psychiatry Investig 13(1):112
Wee ZY, Yong SWL, Chew QH, Guan C, Lee TS, Sim K (2019) Actigraphy studies and clinical and biobehavioural correlates in schizophrenia: a systematic review. J Neural Transm 126(5):531
Witting W, Kwa I, Eikelenboom P, Mirmiran M, Swaab DF (1990) Alterations in the circadian rest-activity rhythm in aging and Alzheimer’s disease. Biol Psychiatry 27(6):563
Berle JO, Hauge ER, Oedegaard KJ, Holsten F, Fasmer OB (2010) Actigraphic registration of motor activity reveals a more structured behavioural pattern in schizophrenia than in major depression. BMC Res Notes 3(1):1
Wulff K, Gatti S, Wettstein JG, Foster RG (2010) Sleep and circadian rhythm disruption in psychiatric and neurodegenerative disease. Nat Rev Neurosc 11(8):589
Murray G, Gottlieb J, Hidalgo MP, Etain B, Ritter P, Skene DJ, Garbazza C, Bullock B, Merikangas K, Zipunnikov V et al (2020) Measuring circadian function in bipolar disorders: empirical and conceptual review of physiological, actigraphic, and self-report approaches. Bipolar Disord 22(7):693
Martin JL, Jeste DV, Ancoli-Israel S (2005) Older schizophrenia patients have more disrupted sleep and circadian rhythms than age-matched comparison subjects. J Psychiatric Res 39(3):251
Domingues A, Paiva T, Sanches JM (2013) Sleep and wakefulness state detection in nocturnal actigraphy based on movement information. IEEE Trans Biomed Eng 61(2):426
Li X, Zhang Y, Jiang F, Zhao H (2020) A novel machine learning unsupervised algorithm for sleep/wake identification using actigraphy. Chronobiol Int. https://doi.org/10.1080/07420528.2020.1754848
Bengio Y et al (1999) Markovian models for sequential data. Neural Comput Surv 2(199):129
Brémaud P (2020) Probability theory and stochastic processes. Springer, Cham
Banachewicz K, Lucas A, Van Der Vaart A (2008) Modelling portfolio defaults using hidden Markov models with covariates. Econom J 11(1):155
Martin J, Marler M, Shochat T, Ancoli-Israel S (2000) Circadian rhythms of agitation in institutionalized patients with Alzheimer’s disease. Chronobiol Int 17(3):405
Bilmes JA et al (1998) A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. Int Comput Sci Inst 4(510):126
Vittinghoff E, McCulloch CE (2007) Relaxing the rule of ten events per variable in logistic and cox regression. Am J Epidemiol 165(6):710
Pavlou M, Ambler G, Seaman S, De Iorio M, Omar RZ (2016) Review and evaluation of penalised regression methods for risk prediction in low-dimensional data with few events. Stat Med 35(7):1159
Sano W, Nakamura T, Yoshiuchi K, Kitajima T, Tsuchiya A, Esaki Y, Yamamoto Y, Iwata N (2012) Enhanced persistency of resting and active periods of locomotor activity in schizophrenia. PloS one 7(8):e43539
Lauerma H, Niskanen L, Lehtinen I, Holmstroem R (1994) Abnormal lateralization of motor activity during sleep in schizophrenia. Schizophrenia research 14(1):65
Jakobsen P, Garcia-Ceja E, Stabell LA, Oedegaard KJ, Berle JO, Thambawita V, Hicks, SA, Halvorsen P, Fasmer OB, Riegler MA (2020) In: 2020 IEEE 33rd international symposium on computer-based medical systems (CBMS) (IEEE, 2020) pp 303–308
Scott J, Vaaler AE, Fasmer OB, Morken G, Krane-Gartiser K (2017) A pilot study to determine whether combinations of objectively measured activity parameters can be used to differentiate between mixed states, mania, and bipolar depression. Int J Bipolar Disord 5(1):5
Gonçalves BS, Cavalcanti PR, Tavares GR, Campos TF, Araujo JF (2014) Nonparametric methods in actigraphy: an update. Sleep Sci 7(3):158
Zuurbier LA, Luik AI, Hofman A, Franco OH, Van Someren EJ, Tiemeier H (2015) Fragmentation and stability of circadian activity rhythms predict mortality: the Rotterdam study. Am J Epidemiol 181(1):54
McFadden D et al (1973) Conditional logit analysis of qualitative choice behavior
SimulaMet. Simula datasets. https://datasets.simula.no
Matthews BW (1975) Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochim Biophys Acta (BBA) Protein Struct 405(2):442
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Boeker, M., Hammer, H.L., Riegler, M.A. et al. Prediction of schizophrenia from activity data using hidden Markov model parameters. Neural Comput & Applic 35, 5619–5630 (2023). https://doi.org/10.1007/s00521-022-07845-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07845-7