Predicting attention-deficit/hyperactivity disorder severity from psychosocial stress and stress-response genes: a random forest regression approach

Abstract

Identifying genetic variants contributing to attention-deficit/hyperactivity disorder (ADHD) is complicated by the involvement of numerous common genetic variants with small effects, interacting with each other as well as with environmental factors, such as stress exposure. Random forest regression is well suited to explore this complexity, as it allows for the analysis of many predictors simultaneously, taking into account any higher-order interactions among them. Using random forest regression, we predicted ADHD severity, measured by Conners’ Parent Rating Scales, from 686 adolescents and young adults (of which 281 were diagnosed with ADHD). The analysis included 17 374 single-nucleotide polymorphisms (SNPs) across 29 genes previously linked to hypothalamic–pituitary–adrenal (HPA) axis activity, together with information on exposure to 24 individual long-term difficulties or stressful life events. The model explained 12.5% of variance in ADHD severity. The most important SNP, which also showed the strongest interaction with stress exposure, was located in a region regulating the expression of telomerase reverse transcriptase (TERT). Other high-ranking SNPs were found in or near NPSR1, ESR1, GABRA6, PER3, NR3C2 and DRD4. Chronic stressors were more influential than single, severe, life events. Top hits were partly shared with conduct problems. We conclude that random forest regression may be used to investigate how multiple genetic and environmental factors jointly contribute to ADHD. It is able to implicate novel SNPs of interest, interacting with stress exposure, and may explain inconsistent findings in ADHD genetics. This exploratory approach may be best combined with more hypothesis-driven research; top predictors and their interactions with one another should be replicated in independent samples.

Challenges in ADHD care for ethnic minority children: A review of the current literature

“…Another explanation for overidentification of ADHD among ethnic minority children is that existing assessment tools (e.g., the Child Behavior Checklist; Lambert, Rowan, Lyubansky, & Russ, 2002) do not adequately capture ADHD manifestation in ethnic minorities. Alternatively, it is possible that ethnic minority children have increased risk for ADHD-related behaviors due to high exposure to etiological risk agents (Breslau & Chilcoat, 2000; DuPaul et al., 1998; Epstein et al., 2005), which increase the risk of ADHD either directly or through gene–environment interactions (van der Meer et al., 2017). Further research is needed to assess the extent to which these etiological risks play a role in producing elevated rates of ADHD symptoms among ethnic minority children.…”

Use of machine learning to classify adult ADHD and other conditions based on the Conners’ Adult ADHD Rating Scales

“…Evaluating PET imaging and genetic predictors within the serotonergic system, an accuracy of .82 could be achieved for classification of ADHD and controls using Random Forest with fivefold cross-validation 29 . The Random Forest approach was used to investigate how multiple genetic and environmental factors jointly contribute to ADHD, or to examine whether hyperactivity persists in male and female adults with ADHD 30 , 31 . Teicher et al were able to demonstrate that a computerized activity measure was best able to differentiate between adults with ADHD and controls (AUC = .83) 31 .…”

Effects of maternal immune activation in porcine transcript isoforms of neuropeptide and receptor genes

“…Some MIA associations with genes detected in the present study were also established at the DNA variant level. For example, single nucleotide polymorphism in or near ADCYAP receptor type I (ADCYAP1R1), NPS receptor (NPSR1), estrogen receptor 1 (ESR1), SRSF protein kinase 2 (SRPK2) genes have been associated with autism spectrum disorders, Alzheimer's disease behavioral traits, anxiety, impulsivity and attention deficit-related traits [21,[54][55][56][57][58][59].…”