Adolescent ADHD and electrophysiological reward responsiveness: A machine learning approach to evaluate classification accuracy and prognosis

György Hámori; Bálint File; Richárd Fiáth; Bea Pászthy; János M Réthelyi; István Ulbert; Nóra Bunford

doi:10.1016/j.psychres.2023.115139

Adolescent ADHD and electrophysiological reward responsiveness: A machine learning approach to evaluate classification accuracy and prognosis

Psychiatry Res. 2023 May:323:115139. doi: 10.1016/j.psychres.2023.115139. Epub 2023 Mar 4.

Authors

György Hámori¹, Bálint File², Richárd Fiáth³, Bea Pászthy⁴, János M Réthelyi⁵, István Ulbert³, Nóra Bunford⁶

Affiliations

¹ Clinical and Developmental Neuropsychology Research Group, Research Centre for Natural Sciences, Institute of Cognitive Neuroscience and Psychology, Magyar Tudósok körútja 2, Budapest 1117, Hungary; Department of Cognitive Science, Faculty of Natural Sciences, Budapest University of Technology and Economics, Műegyetem rkp. 3., Budapest H-1111, Hungary.
² Research Centre for Natural Sciences, Integrative Neuroscience Research Group, Institute of Cognitive Neuroscience and Psychology, Magyar Tudósok körútja 2, Budapest 1117, Hungary; Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/A, Budapest 1083, Hungary; Theoretical Neuroscience and Complex Systems Research Group, Wigner Research Centre for Physics, Konkoly-Tege Miklós út 29-33, Budapest 1121, Hungary.
³ Research Centre for Natural Sciences, Integrative Neuroscience Research Group, Institute of Cognitive Neuroscience and Psychology, Magyar Tudósok körútja 2, Budapest 1117, Hungary; Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/A, Budapest 1083, Hungary.
⁴ Department of Paediatrics, Semmelweis University, Faculty of Medicine, Bókay János u. 53-54, Budapest 1083, Hungary.
⁵ Department of Psychiatry and Psychotherapy, Semmelweis University, Faculty of Medicine, Balassa u. 6, Budapest 1083, Hungary.
⁶ Clinical and Developmental Neuropsychology Research Group, Research Centre for Natural Sciences, Institute of Cognitive Neuroscience and Psychology, Magyar Tudósok körútja 2, Budapest 1117, Hungary. Electronic address: bunford.nora@ttk.hu.

PMID: 36921508
DOI: 10.1016/j.psychres.2023.115139

Abstract

We evaluated event-related potential (ERP) indices of reinforcement sensitivity as ADHD biomarkers by examining, in N=306 adolescents (M_age=15.78, SD=1.08), the extent to which ERP amplitude and latency variables measuring reward anticipation and response (1) differentiate, in age- and sex-matched subsamples, (i) youth with vs. without ADHD, (ii) youth at-risk for vs. not at-risk for ADHD, and, in the with ADHD subsample, (iii) youth with the inattentive vs. the hyperactive/impulsive (H/I) and combined presentations. We further examined the extent to which ERP variables (2) predict, in the ADHD subsample, substance use (i) concurrently and (ii) prospectively at 18-month follow-up. Linear support vector machine analyses indicated ERPs weakly differentiate youth with/without (65%) - and at-risk for/not at-risk for (63%) - ADHD but better differentiate ADHD presentations (78%). Regression analyses showed in adolescents with ADHD, ERPs explain a considerable proportion of variance (50%) in concurrent alcohol use and, controlling for concurrent marijuana and tobacco use, explain a considerable proportion of variance (87 and 87%) in, and predict later marijuana and tobacco use. Findings are consistent with the dual-pathway model of ADHD. Results also highlight limitations of a dichotomous, syndromic classification and indicate differences in neural reinforcement sensitivity are a promising ADHD prognostic biomarker.

Keywords: ADHD; Adolescent; Biomarker; Event-related potential (ERP); Reinforcement sensitivity.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adolescent
Attention Deficit Disorder with Hyperactivity* / diagnosis
Evoked Potentials / physiology
Humans
Machine Learning
Prognosis
Reward