Gated Hidden Markov Models for Early Prediction of Outcome of Internet-Based Cognitive Behavioral Therapy

  • Negar SafinianainiEmail author
  • Henrik BoströmEmail author
  • Viktor KaldoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11526)


Depression is a major threat to public health and its mitigation is considered to be of utmost importance. Internet-based Cognitive Behavioral Therapy (ICBT) is one of the employed treatments for depression. However, for the approach to be effective, it is crucial that the outcome of the treatment is accurately predicted as early as possible, to allow for its adaptation to the individual patient. Hidden Markov models (HMMs) have been commonly applied to characterize systematic changes in multivariate time series within health care. However, they have limited capabilities in capturing long-range interactions between emitted symbols. For the task of analyzing ICBT data, one such long-range interaction concerns the dependence of state transition on fractional change of emitted symbols. Gated Hidden Markov Models (GHMMs) are proposed as a solution to this problem. They extend standard HMMs by modifying the Expectation Maximization algorithm; for each observation sequence, the new algorithm regulates the transition probability update based on the fractional change, as specified by domain knowledge. GHMMs are compared to standard HMMs and a recently proposed approach, Inertial Hidden Markov Models, on the task of early prediction of ICBT outcome for treating depression; the algorithms are evaluated on outcome prediction, up to 7 weeks before ICBT ends. GHMMs are shown to outperform both alternative models, with an improvement of AUC ranging from 12 to 23%. These promising results indicate that considering fractional change of the observation sequence when updating state transition probabilities may indeed have a positive effect on early prediction of ICBT outcome.


Hidden Markov Models Expectation Maximization Depression Internet-based Cognitive Behavioral Therapy 


  1. 1.
    Belgrave, D.: Machine learning for personalized health (ICML 2018). Accessed 14 Aug 2018
  2. 2.
    Bishop, C.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, New York (2006)zbMATHGoogle Scholar
  3. 3.
    Constantinou, A., Fenton, N., Neil, M.: Integrating expert knowledge with data in Bayesian networks: preserving data-driven expectations when the expert variables remain unobserved. Expert. Syst. Appl. 56, 197–208 (2016)CrossRefGoogle Scholar
  4. 4.
    Fantino, B., Moore, N.: The self-reported montgomery-asberg depression rating scale is a useful evaluative tool in major depressive disorder. BMC Psychiatry 9(1), 26 (2009)CrossRefGoogle Scholar
  5. 5.
    Fung, G., Mangasarian, O., Shavlik, J.: Knowledge-based support vector machine classifiers. In: NIPS (2003)Google Scholar
  6. 6.
    Green, C.: Modelling disease progression in Alzheimer’s disease. Pharm. Econ. 25(9), 735–750 (2007)CrossRefGoogle Scholar
  7. 7.
    Hoiles, W., Van Der Schaar, M.: A non-parametric learning method for confidently estimating patient’s clinical state and dynamics. In: NIPS (2016)Google Scholar
  8. 8.
    Kuusisto, F., Dutra, I., Elezaby, M., Mendonca, E., Shavlik, J., Burnside, E.: Leveraging expert knowledge to improve machine-learned decision support systems. AMIA Jt. Summits Transl. Sci. Proc., 87–91 (2015)Google Scholar
  9. 9.
    Kwak, Y., Yang, Y., Park, S.: Missing data analysis in drug-naïve Alzheimer’s disease with behavioral and psychological symptoms. Yonsei Med. J. 54(4), 825–831 (2013)CrossRefGoogle Scholar
  10. 10.
    Lee, D., Roscoe, J., Russell, G.: Developing Hidden Markov Models for aiding the assessment of preterm babies- health. In: International Conference on Biomedical and Pharmaceutical Engineering, pp. 104–109 (2006)Google Scholar
  11. 11.
    Lenhard, F., et al.: Prediction of outcome in internet delivered cognitive behaviour therapy for paediatric obsessive compulsive disorder: a machine learning approach. Int. J. Methods Psychiatr. Res. 27(1), e1576 (2018)CrossRefGoogle Scholar
  12. 12.
    Mitchell, H., Marshall, A., Zenga, M.: Using the Hidden Markov Model to capture quality of care in lombardy geriatric wards. Oper. Res. Health Care 7, 103–110 (2015)CrossRefGoogle Scholar
  13. 13.
    Montanez, G., Amizadeh, S., Laptev, N.: Inertial Hidden Markov Models: modeling change in multivariate time series. In: AAAI Conference on Artificial Intelligence (2015)Google Scholar
  14. 14.
    Popov, A., Gultyaeva, T., Uvarov, V.: A comparison of some methods for training Hidden Markov Models on sequences with missing observations. In: 2016 11th International Forum on Strategic Technology (IFOST), pp. 431–435 (2016)Google Scholar
  15. 15.
    Reddy, M.: Depression: the disorder and the burden. Indian J. Psychol. Med. 32(1), 1–2 (2010)MathSciNetCrossRefGoogle Scholar
  16. 16.
    Schibbye, P., et al.: Using early change to predict outcome in cognitive behaviour therapy: exploring timeframe, calculation method, and differences of disorder-specific versus general measures. PLoS ONE 9(6), e100614 (2014)CrossRefGoogle Scholar
  17. 17.
    Shirley, K., Small, D., Lynch, K., Maisto, S., Oslin, D.: Hidden Markov Models for alcoholism treatment trial data. Ann. Appl. Stat. 4(1), 366–395 (2010)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Stanculescu, I., Williams, C., Freer, Y.: Autoregressive Hidden Markov Models for the early detection of neonatal sepsis. IEEE J. Biomed. Health Inform. 18(5), 1560–1570 (2014)CrossRefGoogle Scholar
  19. 19.
    Titov, N., et al.: ICBT in routine care: a descriptive analysis of successful clinics in five countries. Internet Interv. 13, 108–115 (2018)CrossRefGoogle Scholar
  20. 20.
    Wallert, J., et al.: Predicting adherence to internet-delivered psychotherapy for symptoms of depression and anxiety after myocardial infarction: machine learning insights from the u-care heart randomized controlled trial. J. Med. Internet Res. 20(10), e10754 (2018)CrossRefGoogle Scholar
  21. 21.
    Wartella, E.A.: The Prevention and Treatment of Missing Data in Clinical Trials. National Academies Press, Washington, D.C. (2010)Google Scholar
  22. 22.
    Williams, A., Andrews, G.: The effectiveness of internet cognitive behavioural therapy (ICBT) for depression in primary care: a quality assurance study. PLoS ONE 8(2), E57447 (2013)CrossRefGoogle Scholar
  23. 23.
    Xing, Z., Pei, J., Keogh, E.: A brief survey on sequence classification. ACM SIGKDD Explor. Newsl. 12(1), 40–48 (2010)CrossRefGoogle Scholar
  24. 24.
    Yoon, B., Vaidyanathan, P.: Context-sensitive Hidden Markov Models for modeling long-range dependencies in symbol sequences. IEEE Trans. Signal Process. 54(11), 4169–4184 (2006)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Electrical Engineering and Computer ScienceKTH Royal Institute of TechnologyStockholmSweden
  2. 2.Department of Psychology, Faculty of Health and Life SciencesLinnaeus UniversityVäxjöSweden
  3. 3.Centre for Psychiatry Research, Department of Clinical NeuroscienceKarolinska Institutet, and Stockholm Health Care Services, Stockholm County CouncilStockholmSweden

Personalised recommendations