A Data-Driven Exploration of Hypotheses on Disease Dynamics

  • Marcos L. P. BuenoEmail author
  • Arjen Hommersom
  • Peter J. F. Lucas
  • Joost Janzing
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11526)


Unsupervised learning is often used to obtain insight into the underlying structure of medical data. In this paper, we show that unsupervised methods, in particular hidden Markov models, can go beyond this by guiding the generation of clinical outcome measures and hypotheses, which play a crucial role in medical research. The usage of the data-driven approach facilitates selecting which hypotheses to further investigate. We demonstrate this by using clinical trial data for psychotic depression treatment as a case study. The discovered latent structure and proposed outcome are shown to provide new insight into the heterogeneity of psychotic depression in terms of predictive symptoms.


Machine learning Psychiatry Depression Latent variable Hidden Markov model Unsupervised learning Outcome measure 



This work was partially funded by project “NORTE-01-0145-FEDER-000016” (NanoSTIMA). NanoSTIMA is financed by the North Portugal Regional Operational Programme (NORTE2020), under the PORTUGAL 2020 Partnership Agreement, and through the European Regional Development Fund (ERDF).


  1. 1.
    Ahlqvist, E., et al.: Novel subgroups of adult-onset diabetes and their association with outcomes: a data-driven cluster analysis of six variables. Lancet Diab. Endocrinol. 6(5), 361–369 (2018)CrossRefGoogle Scholar
  2. 2.
    Bueno, M.L.P., Hommersom, A., Lucas, P.J.F., Linard, A.: Asymmetric hidden Markov models. Intl. J. Approximate Reasoning 88, 169–191 (2017)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Hamilton, M.: A rating scale for depression. J. Neurol. Neurosurg. Psychiatry 23(1), 56–62 (1960)CrossRefGoogle Scholar
  4. 4.
    Hosenfeld, B., et al.: Major depressive disorder as a nonlinear dynamic system: bimodality in the frequency distribution of depressive symptoms over time. BMC Psychiatry 15(1), 222 (2015)CrossRefGoogle Scholar
  5. 5.
    IsHak, W.W., et al.: The recovery index: a novel approach to measuring recovery and predicting remission in major depressive disorder. J. Affect Disord. 208, 369–374 (2017)CrossRefGoogle Scholar
  6. 6.
    Meier, J., Dietz, A., Boehm, A., Neumuth, T.: Predicting treatment process steps from events. J Biomed. Inform. 53, 308–319 (2015)CrossRefGoogle Scholar
  7. 7.
    Paoletti, M., et al.: Explorative data analysis techniques and unsupervised clustering methods to support clinical assessment of chronic obstructive pulmonary disease (COPD) phenotypes. J. Biomed. Inform. 42(6), 1013–1021 (2009)CrossRefGoogle Scholar
  8. 8.
    Paulus, M.P., et al.: Latent variable analysis of positive and negative valence processing focused on symptom and behavioral units of analysis in mood and anxiety disorders. J. Affect. Disord. 216, 17–29 (2017)CrossRefGoogle Scholar
  9. 9.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  10. 10.
    Rothschild, A.J.: Challenges in the treatment of major depressive disorder with psychotic features. Schizophrenia Bull. 39(4), 787–796 (2013)CrossRefGoogle Scholar
  11. 11.
    Seltman, H.J., Mitchell, S., Sweet, R.A.: A Bayesian model of psychosis symptom trajectory in Alzheimer’s disease. Int. J. Geriatr. Psychiatry 31(2), 204–210 (2016)CrossRefGoogle Scholar
  12. 12.
    Wijkstra, J., Lijmer, J., Burger, H., Cipriani, A., Geddes, J., Nolen, W.: Pharmacological treatment for psychotic depression. Cochrane Database Syst. Rev. 7 (2015)Google Scholar
  13. 13.
    Wijkstra, J., et al.: Treatment of unipolar psychotic depression: a randomized, double-blind study comparing imipramine, venlafaxine, and venlafaxine plus quetiapine. Acta Psychiatr. Scand. 121(3), 190–200 (2010)CrossRefGoogle Scholar
  14. 14.
    Yet, B., Perkins, Z., Fenton, N., Tai, N., Marsh, W.: Not just data: a method for improving prediction with knowledge. J. Biomed. Inform. 48, 28–37 (2014)CrossRefGoogle Scholar
  15. 15.
    Zhang, N.L., Nielsen, T.D., Jensen, F.V.: Latent variable discovery in classification models. Artif. Intell. Med. 30(3), 283–299 (2004)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Marcos L. P. Bueno
    • 1
    • 2
    Email author
  • Arjen Hommersom
    • 1
    • 3
  • Peter J. F. Lucas
    • 1
    • 4
  • Joost Janzing
    • 5
  1. 1.iCISRadboud University NijmegenNijmegenThe Netherlands
  2. 2.Department of Computer ScienceFederal University of UberlândiaUberlândiaBrazil
  3. 3.Faculty of Management, Science and TechnologyOpen UniversityHeerlenThe Netherlands
  4. 4.LIACSLeiden UniversityLeidenThe Netherlands
  5. 5.Department of PsychiatryRadboud UMCNijmegenThe Netherlands

Personalised recommendations