The Oregon ADHD-1000: A new longitudinal data resource enriched for clinical cases and multiple levels of analysis

Abstract

The fields of developmental psychopathology, developmental neuroscience, and behavioral genetics are increasingly moving toward a data sharing model to improve reproducibility, robustness, and generalizability of findings. This approach is particularly critical for understanding attention-deficit/hyperactivity disorder (ADHD), which has unique public health importance given its early onset, high prevalence, individual variability, and causal association with co-occurring and later developing problems. A further priority concerns multi-disciplinary/multi-method datasets that can span different units of analysis. Here, we describe a public dataset using a case-control design for ADHD that includes: multi-method, multi-measure, multi-informant, multi-trait data, and multi-clinician evaluation and phenotyping. It spans > 12 years of annual follow-up with a lag longitudinal design allowing age-based analyses spanning age 7-19 + years with a full age range from 7 to 21. Measures span genetic and epigenetic (DNA methylation) array data; EEG, functional and structural MRI neuroimaging; and psychophysiological, psychosocial, clinical and functional outcomes data. The resource also benefits from an autism spectrum disorder add-on cohort and a cross sectional case-control ADHD cohort from a different geographical region for replication and generalizability. Datasets allowing for integration from genes to nervous system to behavior represent the "next generation" of researchable cohorts for ADHD and developmental psychopathology.

Keywords: Attention-deficit/hyperactivity disorder; Case-control longitudinal; Design; Genetic and epigenetic array; Neuroimaging; Public dataset; Pyschophysiological.

Fig. 1.

Overview of Participant Recruitment Fig. 1 illustrates the participant flow into this study using a case-finding, best-estimate procedure. On the left top moving to the right, the primary Oregon-ADHD-1000 cohort was recruited through widespread public outreach and mass mailings and then screened to find cases of ADHD and non-ADHD typically developing youth who met study inclusion criteria. “Other” represents cases in which only one reporter rated notable symptoms, or the case was subthreshold/NOS (e.g. 4 symptoms with impairment), or the child was taking a disqualifying medication (e.g.anti-depressant) at baseline. The same procedure was used for the generalizability sample named the Michigan-ADHD-1000 (not depicted to maintain readability; described below). On the bottom left to right, the ASD cohort (also described later in the text) was recruited from hospital records and then diagnostic status was confirmed by a similar best-estimate multi-clinician review procedure as used in the ADHD-1000. Please refer to the main text for full details on recruitment and diagnosis.

Fig. 2

Repeated Assessment of Multiple Datatypes Each participant is represented by an individual line with each visit represented as a dot along the line (A). The longitudinal collection of each datatype is represented in B. Details on individual visits per participant are provided in the Supplementary Information. Blue=neuroimaging, yellow=cognitive tasks (e.g. executive functioning), green=peripheral psychophysiology as represented by electrocardiography(ECG).

Fig. 3

Data types available at each age This resource provides numerous data types across a wide range of ages, enabling multi-level age-based analyses. (A) Total observations at each year of age and (B) the distribution of those observations across Neuroimaging, Cognition and Electrocardiology (ECG) data types. All available data types are provided in the Supplementary Information.