Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

Abstract

A mixed literature implicates atypical connectivity involving attentional, reward and task inhibition networks in ADHD. The neural mechanisms underlying the utility of behavioral tasks in ADHD diagnosis are likewise underexplored. We hypothesized that a machine-learning classifier may use task-based functional connectivity to compute a joint probability function that identifies connectivity signatures that accurately predict ADHD diagnosis and performance on a clinically-relevant behavioral task, providing an explicit neural mechanism linking behavioral phenotype to diagnosis. We analyzed archival MRI and behavioral data of 80 participants (64 male) who had completed the go/no-go task from the longitudinal follow-up of the Multimodal Treatment Study of ADHD (MTA 168) (mean age = 24 years). Cross-mutual information within a functionally-defined mask measured functional connectivity for each task run. Multilayer feedforward classifier models identified the subset of functional connections that predicted clinical diagnosis (ADHD vs. Control) and split-half performance on the Iowa Gambling Task (IGT). A sample of random models trained on functional connectivity profiles predicted validation set clinical diagnosis and IGT performance with 0.91 accuracy and d′ > 2.9, indicating very high sensitivity and specificity. We identified the most diagnostic functional connections between visual and ventral attentional networks and the anterior default mode network. Our results show that task-based functional connectivity is a biomarker of ADHD. Our analytic framework provides a template approach that explicitly ties behavioral assessment measures to both clinical diagnosis, and functional connectivity. This may differentiate otherwise similar diagnoses, and promote more efficacious intervention strategies.

The New Field of Network Physiology: Building the Human Physiolome

“…New computational and analytical approaches are needed to extract information from complex data, to infer transient interactions between dynamically changing systems, and to quantify global behavior at the organism level generated by networks of interactions that are function of time. In fact, in recent years, we have already witnessed the broad impact of introducing novel concepts and methods derived from modern statistical physics and network theory to biology and medicine, shifting the paradigm from reductionism to a new integrative framework essential to address fundamentally new problems in systems biology (Yao et al, 2019;Prats-Puig et al, 2020;Corkey and Deeney, 2020;Rizi et al, 2021;Barajas-Martínez et al, 2020), neuroscience (Castelluzzo et al, 2020;Pa¨eske et al, 2020;Fesce, 2020;Stramaglia et al, 2021), physiology (Podobnik et al, 2020;Zmazek et al, 2021), clinical medicine (Loscalzo and Barabasi, 2011;Delussi et al, 2020;Li et al, 2020;Liu et al, 2020;McNorgan et al, 2020;Tan et al, 2020;Haug et al, 2021;Liu et al, 2021) and even drug discovery (Hopkins, 2008). A central focus of research within this integrative framework is the interplay between structural connectivity and functional dependency, a key problem in neuroscience, brain research (Bullmore and Sporns, 2009;Gallos et al, 2012;Rothkegel and Lehnertz, 2014;Liu et al, 2015a;Bolton et al, 2020;Wang and Liu, 2020) and human physiology (Pereira-Ferrero et al, 2019;Lavanga et al, 2020;Barajas-Martínez et al, 2021;Gao et al, 2018;Balagué et al, 2020;Porta et al, 2017;Lioi et al, ...…”

Machine learning and MRI-based diagnostic models for ADHD: are we there yet?

“…Ten other studies focused only on children and/or adolescents (under age 18). Only five studies examined classification models for older adults [45,51,[62][63][64]. Overall, the difference in accuracy across the three types of age compositions was not significant (F (2,55) =1.…”

Dynamic configuration of large-scale cortical networks during an inhibitory task accounts for heterogeneity in attention-deficit/hyperactivity disorder traits

“…Instead, examining patterns of connectivity between cortical regions in the wide-spread functional networks important for cognitive control appears to be necessary. This conclusion-that distinct ADHD symptoms may be linked to altered connectivity between cortical regions during the execution/inhibition of motor responses-has increasingly been made within the broad shift towards understanding ADHD through a network-based approach, rather than a regional-abnormality based approach (5,14,24,25,26). This network approach is also in line with research examining the neural correlates of response inhibition, which has argued against specific regions functionally specialized for inhibitory processing in favour of a domain-general class of 'network mechanisms', where connectivity patterns initiated by the fronto-parietal network account for a variety of functions during cognitive control (27, 28).…”

“…Although inhibitory deficits are pronounced in those with ADHD, some evidence suggests individual differences in the mechanisms underlying the ability to execute/inhibit motor responses might specifically account for hyperactive/impulsive traits (13,14). In EEG research, for example, compared to the inattentive subtype, those with the combined subtype show higher amplitude beta oscillations at electrodes over the sensorimotor cortex during a cued-flanker inhibitory task (thought to reflect weaker motor response planning (12)).…”

“…One approach recently used in ADHD research is that of task-based network measures, which characterize the dynamic changes in large-scale functional network organization during distinct cognitive processes (14,29,30). Since these changes are closely linked to behaviour, it is thought that task-based approaches might better capture sources of ADHD heterogeneity than resting-state approaches (14,29,31). A network approach might also further the use of EEG in clinical ADHD research.…”