Advertisement

Predictive Strength of Bayesian Networks for Diagnosis of Depressive Disorders

  • Blessing OjemeEmail author
  • Audrey Mbogho
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 56)

Abstract

Increasing cases of misdiagnosis of mental disorders in Nigeria despite the use of the international standards provided in the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) and International Classification of Diseases (ICD-10) calls for an approach that takes cognizance of the socio-economic difficulties on the ground. While a growing recognition of the potential of artificial intelligence (AI) techniques in modeling clinical procedures has led to the design of various systems to assist clinicians in decision-making tasks in physical diseases, little attention has been paid to exploring the same techniques in the mental health domain. This paper reports the preliminary findings of a study to investigate the predictive strength of Bayesian networks for depressive disorders diagnosis. An automatic Bayesian model was constructed and tested with a real-hospital dataset of 580 depression patients of different categories and 23 attributes. The model predicted depression and its severity with high efficiency.

Keywords

Artificial intelligence Bayesian networks Mental health Depression disorders Psychiatric diagnosis 

References

  1. 1.
    Bayes, T.: An essay towards solving a problem in the doctrine of chances. By the Late Rev. Mr. Bayes, F. R. S. communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S. Philos. Trans. R. Soc. London 53(0), 370–418 (1763)Google Scholar
  2. 2.
    Heckerman, D.: Bayesian networks for data mining. Data Min. Knowl. Discov. 119(1), 79–119 (1997)CrossRefGoogle Scholar
  3. 3.
    Nikovski, D.: Constructing Bayesian networks for medical diagnosis from incomplete and partially correct statistics. IEEE Trans. Knowl. Data Eng. 12(4), 1–18 (2000)CrossRefGoogle Scholar
  4. 4.
    Tylman, W., Waszyrowski, T., Napieralski, A., Kamiński, M., Trafidło, T., Kulesza, Z., Kotas, R., Marciniak, P., Tomala, R., Wenerski, M.: Real-time prediction of acute cardiovascular events using hardware-implemented Bayesian networks. Comput. Biol. Med. (2015)Google Scholar
  5. 5.
    Su, C., Andrew, A., Karagas, M.R., Borsuk, M.E.: Using Bayesian networks to discover relations between genes, environment, and disease. BioData Min. 6(1), 6 (2013)Google Scholar
  6. 6.
    Gangwar, M., Mishra, R.B., Yadav, R.S.: Classical and intelligent computing methods in psychiatry and neuropsychitry : an overview. Int. J. Adv. Res. IT Eng. 3(12) (2014)Google Scholar
  7. 7.
    Ganasen, K.A., Parker, S., Hugo, C.J., Stein, D.J., Emsley, R.A., Seedat, S.: Mental health literacy: focus on developing countries. Afr. J. Psychiatry 11(1), 23–28 (2008)CrossRefGoogle Scholar
  8. 8.
    Chattopadhyay, S.: A neuro-fuzzy approach for the diagnosis of depression. Elsevier Appl. Comput. Inform. in Press, 19 (2014)Google Scholar
  9. 9.
    Doherty, G., Coyle, D., Matthews, M.: Design and evaluation guidelines for mental health technologies. Interact. Comput. 22(4), 243–252 (2010)CrossRefGoogle Scholar
  10. 10.
    James, B., Jenkins, R., Lawani, A., Omoaregba, J.: Depression in primary care: the knowledge, attitudes and practice of general practitioners in Benin City, Nigeria. S Afr Fam Pr. 54(1), 55–60 (2012)Google Scholar
  11. 11.
    Ferrari, A.J., Charlson, F.J., Norman, R.E., Patten, S.B., Freedman, G., Murray, C.J.L., Vos, T., Whiteford, H.: Burden of depressive disorders by country, sex, age, and year: findings from the global burden of disease study 2010. PLoS Med. 10(11) (2013)Google Scholar
  12. 12.
    Salihu, A.S.: Impact of somatic symptoms on identification of depression among general outpatients by family physicians. Open J. Psychiatry 5, 278–284 (2015)Google Scholar
  13. 13.
    Ahmed, K., Bhugra, D.: Depression across ethnic minority cultures: diagnostic issues. World Cult. Psychiatry Res. Rev. 2(3), 51 (2007)Google Scholar
  14. 14.
    Huang, S.H., LePendu, P., Iyer, S.V., Tai-Seale, M., Carrell, D., Shah, N.H.: Toward personalizing treatment for depression: predicting diagnosis and severity. J. Am. Med. Inform. Assoc. 1–7 (2014)Google Scholar
  15. 15.
    WHO: Depression: a global public health concern. WHO Dep. Ment. Heal. Subst. Abus. 1–8 (2012). http://www.who.int/mental_health/management/depression/who_paper_depression_wfmh_2012.pdf
  16. 16.
    Baasher, T.A., Carstairs, G.M., Giel, R., Hassler, F.R.: Mental health services in developing countries. WHO Seminar on the Organisation of Mental Health Services. World Health Organisation, Geneva (1975)Google Scholar
  17. 17.
    Sumathi, M.R., Poorna, B.: A bayesian framework for diagnosing depression level of adolescents. Int. Conf. Comput. Intell. Syst. 4(March), 1350–1354 (2015)Google Scholar
  18. 18.
    Curiac, D.-I., Vasile, G., Banias, O., Volosencu, C., Albu, A.: Bayesian network model for diagnosis of psychiatric diseases. In: Proceedings of ITI 2009 31st International Conference on Information Technology Interfaces, pp. 61–66 (2009_Google Scholar
  19. 19.
    Chang, Y.-S., Fan, C.-T., Lo, W.-T., Hung, W.-C., Yuan, S.-M.: Mobile cloud-based depression diagnosis using an ontology and a Bayesian network. Futur. Gener. Comput. Syst. 43–44, 87–98 (2015)CrossRefGoogle Scholar
  20. 20.
    Bouckaert, R.R., Frank, E., Hall, M., Kirkby, R., Reutemann, P., Seewald, A., Scuse, D.: WEKA Manual for Version 3-7-12. University of Waikato, Hamilton, New Zealand (2014)Google Scholar
  21. 21.
    Tversky, A., Kahneman, D.: Judgment under Uncertainty: Heuristics and Biases. American Association for the Advancement of Science, New Series, pp. 1124–1131 (1974)Google Scholar
  22. 22.
    Witten, I., Frank, E., Hall, M.: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishers, Third Edit (2011)Google Scholar
  23. 23.
    Shojaei Estabragh, Z., Riahi Kashani, M.M., Jeddi Moghaddam, F., Sari, S., Taherifar, Z., Moradi Moosavy, S., Sadeghi Oskooyee, K.: Bayesian network modeling for diagnosis of social anxiety using some cognitive-behavioral factors. Netw. Model. Anal. Heal. Inform. Bioinforma. 2(4), 257–265 (2013)Google Scholar
  24. 24.
    Oteniya, L.: Bayesian Belief Networks for Dementia Diagnosis and Other Applications: A Comparison of Hand-Crafting and Construction using A Novel Data Driven Technique. A PhD Thesis, Department of Computing Science and Mathematics, University of Stirling, 2008Google Scholar
  25. 25.
    Saito, T., Rehmsmeier, M.: The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3), e0118432 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Cape TownRondeboschSouth Africa
  2. 2.Department of Mathematics and PhysicsPwani UniversityKilifiKenya

Personalised recommendations