Display options
Cite
Wong HK, Tiffin PA, Chappell MJ, et al. Personalized Medication Response Prediction for Attention-Deficit Hyperactivity Disorder: Learning in the Model Space vs. Learning in the Data Space. Front Physiol. 2017;8:199doi: 10.3389/fphys.2017.00199.
Wong, H. K., Tiffin, P. A., Chappell, M. J., Nichols, T. E., Welsh, P. R., Doyle, O. M., Lopez-Kolkovska, B. C., Inglis, S. K., Coghill, D., Shen, Y., & Tiño, P. (2017). Personalized Medication Response Prediction for Attention-Deficit Hyperactivity Disorder: Learning in the Model Space vs. Learning in the Data Space. Frontiers in physiology, 8199. https://doi.org/10.3389/fphys.2017.00199
Wong, Hin K, et al. "Personalized Medication Response Prediction for Attention-Deficit Hyperactivity Disorder: Learning in the Model Space vs. Learning in the Data Space." Frontiers in physiology vol. 8 (2017): 199. doi: https://doi.org/10.3389/fphys.2017.00199
Wong HK, Tiffin PA, Chappell MJ, Nichols TE, Welsh PR, Doyle OM, Lopez-Kolkovska BC, Inglis SK, Coghill D, Shen Y, Tiño P. Personalized Medication Response Prediction for Attention-Deficit Hyperactivity Disorder: Learning in the Model Space vs. Learning in the Data Space. Front Physiol. 2017 Apr 11;8:199. doi: 10.3389/fphys.2017.00199. eCollection 2017. PMID: 28443027; PMCID: PMC5387107.
Copy Download .nbib Format: NLM
Share it on

Front Physiol. 2017 Apr 11;8:199. doi: 10.3389/fphys.2017.00199. eCollection 2017.

Personalized Medication Response Prediction for Attention-Deficit Hyperactivity Disorder: Learning in the Model Space vs. Learning in the Data Space.

Frontiers in physiology

Hin K Wong, Paul A Tiffin, Michael J Chappell, Thomas E Nichols, Patrick R Welsh, Orla M Doyle, Boryana C Lopez-Kolkovska, Sarah K Inglis, David Coghill, Yuan Shen, Peter Tiño

Affiliations

  1. Warwick Manufacturing Group, Institute of Digital Healthcare, University of WarwickCoventry, UK.
  2. Mental Health and Addiction Research Group, Department of Health Sciences, University of YorkYork, UK.
  3. School of Engineering, University of WarwickCoventry, UK.
  4. School of Psychology, Newcastle UniversityNewcastle upon Tyne, UK.
  5. Centre for Neuroimaging Sciences, King's College LondonLondon, UK.
  6. Division of Maternal and Child Health Sciences, Ninewells Hospital and Medical School, University of DundeeDundee, UK.
  7. Departments of Paediatrics and Psychiatry, University of MelbourneMelbourne, VIC, Australia.
  8. School of Computer Science, University of BirminghamBirmingham, UK.

PMID: 28443027 PMCID: PMC5387107 DOI: 10.3389/fphys.2017.00199

Abstract

Attention-Deficit Hyperactive Disorder (ADHD) is one of the most common mental health disorders amongst school-aged children with an estimated prevalence of 5% in the global population (American Psychiatric Association, 2013). Stimulants, particularly methylphenidate (MPH), are the first-line option in the treatment of ADHD (Reeves and Schweitzer, 2004; Dopheide and Pliszka, 2009) and are prescribed to an increasing number of children and adolescents in the US and the UK every year (Safer et al., 1996; McCarthy et al., 2009), though recent studies suggest that this is tailing off, e.g., Holden et al. (2013). Around 70% of children demonstrate a clinically significant treatment response to stimulant medication (Spencer et al., 1996; Schachter et al., 2001; Swanson et al., 2001; Barbaresi et al., 2006). However, it is unclear which patient characteristics may moderate treatment effectiveness. As such, most existing research has focused on investigating univariate or multivariate correlations between a set of patient characteristics and the treatment outcome, with respect to dosage of one or several types of medication. The results of such studies are often contradictory and inconclusive due to a combination of small sample sizes, low-quality data, or a lack of available information on covariates. In this paper, feature extraction techniques such as latent trait analysis were applied to reduce the dimension of on a large dataset of patient characteristics, including the responses to symptom-based questionnaires, developmental health factors, demographic variables such as age and gender, and socioeconomic factors such as parental income. We introduce a Bayesian modeling approach in a "learning in the model space" framework that combines existing knowledge in the literature on factors that may potentially affect treatment response, with constraints imposed by a treatment response model. The model is personalized such that the variability among subjects is accounted for by a set of subject-specific parameters. For remission classification, this approach compares favorably with conventional methods such as support vector machines and mixed effect models on a range of performance measures. For instance, the proposed approach achieved an area under receiver operator characteristic curve of 82-84%, compared to 75-77% obtained from conventional regression or machine learning ("learning in the data space") methods.

Keywords: Bayesian inference; attention-deficit hyperactivity disorder; machine learning; methylphenidate; mixed effects model; personalized medicine; prognosis; treatment response

References

  1. BMJ Open. 2016 Apr 26;6(4):e010433 - PubMed
  2. J Gen Intern Med. 2004 May;19(5 Pt 1):460-5 - PubMed
  3. J Dev Behav Pediatr. 2006 Feb;27(1):1-10 - PubMed
  4. Genetics. 2007 Dec;177(4):2243-50 - PubMed
  5. IEEE Trans Biomed Eng. 2013 Mar;60(3):735-42 - PubMed
  6. J Am Acad Child Adolesc Psychiatry. 2001 Feb;40(2):168-79 - PubMed
  7. J Child Psychol Psychiatry. 1997 Jul;38(5):581-6 - PubMed
  8. Psychol Res. 2009 Mar;73(2):136-46 - PubMed
  9. Pharmacotherapy. 2009 Jun;29(6):656-79 - PubMed
  10. Psychometrika. 1965 Jun;30:179-85 - PubMed
  11. IEEE Trans Neural Netw Learn Syst. 2014 Jan;25(1):124-36 - PubMed
  12. Expert Opin Pharmacother. 2004 Jun;5(6):1313-20 - PubMed
  13. Int J Neuropsychopharmacol. 2015 May 10;18(11):pyv052 - PubMed
  14. J Child Adolesc Psychopharmacol. 2012 Jun;22(3):215-25 - PubMed
  15. Syst Rev. 2012 Feb 10;1:10 - PubMed
  16. Cancer. 1950 Jan;3(1):32-5 - PubMed
  17. Eur Child Adolesc Psychiatry. 2006 Dec;15(8):476-95 - PubMed
  18. Child Adolesc Psychiatry Ment Health. 2013 Oct 11;7(1):34 - PubMed
  19. Int J Methods Psychiatr Res. 2015 Jun;24(2):156-69 - PubMed
  20. Arch Gen Psychiatry. 1983 Nov;40(11):1228-31 - PubMed
  21. Br J Psychiatry. 2009 Mar;194(3):273-7 - PubMed
  22. J Am Acad Child Adolesc Psychiatry. 1996 Apr;35(4):409-32 - PubMed
  23. Pediatrics. 1996 Dec;98(6 Pt 1):1084-8 - PubMed
  24. BMJ. 2010 Mar 23;340:c332 - PubMed
  25. BMJ. 2007 Oct 20;335(7624):806-8 - PubMed
  26. Clin Psychol Rev. 2008 Jun;28(5):783-800 - PubMed
  27. Biosci Biotechnol Biochem. 2007 Oct;71(10):2383-92 - PubMed
  28. Assessment. 2008 Sep;15(3):317-28 - PubMed
  29. J Am Acad Child Adolesc Psychiatry. 2006 Nov;45(11):1284-93 - PubMed
  30. J Abnorm Child Psychol. 1985 Mar;13(1):155-67 - PubMed
  31. J Child Psychol Psychiatry. 2000 Jul;41(5):645-55 - PubMed
  32. Pediatrics. 1983 Jul;72(1):49-55 - PubMed
  33. Behav Res Methods. 2006 Feb;38(1):88-91 - PubMed
  34. Cochrane Database Syst Rev. 2015 Nov 25;(11):CD009885 - PubMed
  35. J Am Acad Child Adolesc Psychiatry. 1989 Jul;28(4):566-73 - PubMed
  36. CMAJ. 2001 Nov 27;165(11):1475-88 - PubMed
  37. PLoS Comput Biol. 2011 Jun;7(6):e1002079 - PubMed
  38. Can Child Adolesc Psychiatr Rev. 2005 Aug;14(Supplement 1):10-5 - PubMed

Publication Types