Aiding diagnosis of attention-deficit/hyperactivity disorder and its subtypes: discriminant function analysis of
Janette L Smith1, Stuart J Johnstone, Robert J Barry
1Brain & Behaviour Research Institute, University of Wollongong, NSW, Australia.
Background:
Robust evidence exists that the brain functioning of children and adolescents with attention-deficit/hyperactivity disorder (AD/HD) differs from that of normal controls. The purpose of this study was to further investigate whether event-related potential (ERP) measures of brain function could be used to reliably classify normal controls versus children and adolescents with two subtypes of AD/HD.
Methods:
Behavioural and topographic ERP data from children aged 8-12 years (n = 75) and adolescents aged 13-18 years (n = 75) were entered into stepwise discriminant function analyses separating controls and subjects with AD/HD, and also subjects with AD/HD-Predominantly Inattentive type (AD/HDin) from those with AD/HD-Combined type (AD/HDcom).
Results:
For children aged 8-12 years, controls and children with AD/HD could be separated with an overall classification accuracy of 73.3%, and the AD/HD subtypes were classified with 69.4% overall accuracy. For adolescents aged 13-18 years, 58.7% of the control vs. AD/HD subjects were correctly classified, and 62.7% of subjects in the subtypes. Classification function coefficients for each of these discriminations are presented for the purposes of cross-validation.
Conclusions:
In children aged 8-12 years, analysis of ERP data may aid a clinician in diagnosing AD/HD, although the clinical utility of ERP analysis is reduced for adolescents aged 13-18 years. Suggestions are made to combine ERP measures with other measures of brain function in order to improve classification accuracy, and also to predict drug response in children diagnosed with AD/HD.
