Designing an accurate system for differentiating children with attention deficit-hyperactivity disorder from oppositional defiant disorder by using artificial neural network

Document Type : Original article

Authors

1 1. Ph.D Student of Exceptional child psychology, Depatment of Psychology and Education, University of Tehran, Tehran, Iran

2 2. Department of Psychology, University of Tehran, Tehran, Iran.

3 3. Associated Professor, Psychiatrist, Faculty of Rehabilitation Scienses, Shahid Beheshti University of Medical Scienses, Tehran, Iran.

4 4. Distinguished Professor, Department of Psychology and Education, University of Tehran, Tehran, Iran

5 5. Associated Professor, Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran.

6 6. Professor, Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran.

Abstract

Background and Aim: Behavioral disorders are one of the most considerable disorders in children during these days. Accurate diagnosis and early identification, especially in disorders with similar sysmptoms, are noticeable and very important. Moreover, most of the affected individuals are rejected by their parents and teachers, decreasing their chances of normal development and their future life will be affected.
Due to many similarities among oppositional defiant disorder and attention deficit-hyperactivity disorder, differentiation of these disorders is challenging, although diagnosing and distinguishing of these disorders are very important.
Materials and Methods: Due to overlapping between oppositional defiant disorder and attention deficit hyperactivity disorder and normal behavior with temporarely aggression, it was tried to design an artificial neural network to assist in accurate distinguishing these classes.
Samples were consisted of 85 children with behavioral disorders (including ADHD and oppositional defiant disorder) and 50 children with normal behavior but temporarly sign of aggresion. Multilayer perceptron neural network was used to designe the system.
Results: The average of accuracy of correct classification with the desined network reacehed to 95.55%. The designed system can be used as a reliable assistant for the psychiatrists and it can increase the diagnosis realiability.
Conclusion: The designed system can differentiate children with behavioral disorders with high accuracy. It can be used as a screening tool for high risk children.

Keywords


  1. Forness SR, Knitzer J. 1992, A New Proposed Definition and Terminology to Replace Serious Emotional Disturbance in Individuals Disabilities Act. School Psychology Review1992; 21: p. 12-20.##
  2. Sadock BJ, Sadock VA. Kaplan & Sadock’s Synopsis of Psychiatry: Behavioral Sciences/Clinical Psychiatry. 2007; 10th Edition. Lippincott Williams & Wilkins.##
  3. Rutter M, Graham P. Psychiatric disorder in 10- and 11-year-old children. Proc R Soc Med 1966; 59: p. 382–387.##
  4. Mitchell A. J. Principles of Psychiatric Classification.  University Department of Psychiatry 1932; 25: p. 1195–1196. ##
  5. Ahuja N. A Short Textbook of Psychiatry India. JAYPEE 2002.##
  6. Harrington R. Assessment of psychiatric disorders in children. Psychiatry 2005; 4: p. 19–22.##
  7. Bruce H. Evans N. Assessment of child psychiatric disorders. Psychiatry 2008; 7: p. 242–245.##
  8. Yevseyeva I. Miettinen K. Räsänen P. Decision support system for attention deficit hyperactivity disorder diagnostics. ORP3 2005; Valencia, pp. 6–10.##
  9. Giedd JN. Castellanos FX. Casey BJ. Kozuch P. King AC. Hamburger SD. Rapoport JL. Quantitative morphology of the corpus callosum in attention deficit hyperactivity disorder. The American Journal of Psychiatry 1994; 151: p.665–669.##
  10. Murias M. Swanson JM. Srinivasan R. Functional connectivity of frontal cortex in healthy and ADHD children reflected in EEG coherence. Cerebral Cortex 2007; 17: p. 1788–1799.##
  11. Özyılmaz L. Yıldırım T. Artificial Neural Networks for Diagnosis of Hepatitis Disease. In International Joint Conference on Neural Networks 2003; 1,p. 586–589.##
  12. Kecman V. Learning and Soft Computing: Support Vector Machines. Neural Networks and Fuzzy Logic Systems (Complex Adaptive Systems) 2001; MIT Press, Cambridge, Massachusetts.##
  13. Langberg JM. Froehlich TE. Loren RE. Martin JE. Epstein JN. Assessing children with ADHD in primary care settings. Expert Review of Neurotherapeutics 2008; 8: p. 627–41##.
  14. Dreyfus G. neural networks: an overview. Neural networks methodology and applications (EBook) 2005; 497.##
  15. Price RK. Spitznagel EL. Downey TJ. Meyer DJ. Risk NK. el-Ghazzawy OG. Applying artificial neural network models to clinical decision making. Psychological Assessment 2000; 12, p. 40–51.##
  16. Delavarian M., Towhidkhah F., Dibajnia P., Gharibzadeh S. Designing a Decision Support System for Distinguishing ADHD from Similar Children Behavioral Disorders. Journal of Medical Systems 2012; 36: p.1335-43.##
  17. Zou Y. Shen Y. Shu L. Wang Y. Feng F. Xu K. Ou Y. Song Y. Zhong Y. Wang M. Liu W. Artificial neural network to assist psychiatric diagnosis. The British Journal of Psychiatry 1996; 169: p. 64–67.##
  18. Tryon, W.W. (2014). Chapter 11 – Clinical Implications of Network Principles 3–12. , Pages 501–561##
  19. Modai I. Staler M. Inbar-Saban N. Saban N. Clinical Decisions for Psychiatric Inpatients and Their Evaluation by a Trained Neural Network.  Methods of Information in Medicine 1993; 32: p. 396-399.##
  20. Helzer JE, Stoltzman RK, Farmer A, Brockington IF, Plesons D, Singerman B, Works J. Comparing the DIS with a DIS/DSM-III-based physician reevaluation. In: Eaton WW, Kessler LG, editors. Epidemiologic field methods in psychiatry: The NIMH Epidemiologic Catchment Area Program . New York: Academic Press 1985;. p. 285–308.##
  21. Kashani JH. Nair SS.Rao VG. Nair J. Reid JC. Relationship of Personality. Environmental and DICA Variables to Adolescent Hopelessness: A Neural Network 'Sensitivity Approach. Journal of the American Academy of Child and Adolescent Psychiatry 1996; 35: p. 640-645. ##
  22. Bashyal SH. Classification of psychiatric disorders using artificial neural network. Lecture Notes in Computer Science 2005; p. 796–800##
  23. Musisi S. Kinyanda E. Nakasujja N. Nakigudde J. A comparison of the behavioral and emotional disorders of primary school-going orphans and non-orphans in Uganda. African Health Sciences 2007; 7: p. 202–213.##
  24. Giannakopoulos G. Kazantzi M. Dimitrakaki C. Tsiantis J. Kolaitis G. Toun Y. Screening for children’s depression symptoms in Greece: the use of the 280 children’s depression inventory in anation-wideschool-based sample.  Child&AdolescentPsychiatry 2009; 18: p. 485–492.##
  25. Bennett, C.C., Hauser, K. (2013). Artificial intelligence framework for simulating clinical decision-making: A Markov decision process approach. Artificial Intelligence in Medicine, Volume 57, Issue 1, January 2013, Pages 9–19##
  26. Ahmadlou, M. and Adeli, H., Wavelet- Synchronization Methodology: A New Approach for EEGbased Diagnosis of ADHD, Clinical EEG and Neuroscience, Vol. 41, No. 1, PP. 1-10, 2010.##

 

  1. Cohen, I.L. , Sudhalter, V., Landon-Jimenez, D., Keogh, M. , A neural network approach to the classification of autism, Journal of Autism and Developmental Disorders, Volume 23, 443-466, 1993##
  2. deFigueiredo, R J., Shankle, W R., Maccato, A., Dick, M B., Mundkur, P., Mena, I., Cotman, C W., Neural-network-based classification of cognitively normal, demented, Alzheimer disease and vascular dementia from single photon emission with computed tomography image data from brain, Proc. Natl. Acad. Sci., Vol. 92, pp. 5530-5534, 1995.##
Volume 4, Issue 1 - Serial Number 1
March and April 2015
Pages 90-98
  • Receive Date: 09 March 2014
  • Revise Date: 22 June 2014
  • Accept Date: 27 October 2014
  • First Publish Date: 21 March 2015