Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder that affects approximately 8%–12% of children worldwide. Throughout an individual’s lifetime, ADHD can significantly increase risk for other psychiatric disorders, educational and occupational failure, accidents, criminality, social disability and addictions. No single risk factor is necessary or sufficient to cause ADHD. The multifactorial causation of ADHD is reflected in the heterogeneity of this disorder, as indicated by its diversity of psychiatric comorbidities, varied clinical profiles, patterns of neurocognitive impairment and developmental trajectories, and the wide range of structural and functional brain anomalies. Although evidence-based treatments can reduce ADHD symptoms in a substantial portion of affected individuals, there is yet no curative treatment for ADHD. A number of theoretical models of the emergence and developmental trajectories of ADHD have been proposed, aimed at providing systematic guides for clinical research and practice. We conducted a comprehensive review of the current status of research in understanding the heterogeneity of ADHD in terms of etiology, clinical profiles and trajectories, and neurobiological mechanisms. We suggest that further research focus on investigating the impact of the etiological risk factors and their interactions with developmental neural mechanisms and clinical profiles in ADHD. Such research would have heuristic value for identifying biologically homogeneous subgroups and could facilitate the development of novel and more tailored interventions that target underlying neural anomalies characteristic of more homogeneous subgroups.
Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.
Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder, which is diagnosed using subjective symptom reports. Machine learning classifiers have been utilized to assist in the development of neuroimaging-based biomarkers for objective diagnosis of ADHD. However, existing basic model-based studies in ADHD report suboptimal classification performances and inconclusive results, mainly due to the limited flexibility for each type of basic classifier to appropriately handle multi-dimensional source features with varying properties. This study applied ensemble learning techniques (ELTs), a meta-algorithm that combine several basic machine learning models into one predictive model in order to decrease variance, bias, or improve predictions, in multimodal neuroimaging data collected from 72 young adults, including 36 probands (18 remitters and 18 persisters of childhood ADHD) and 36 group-matched controls. All currently available optimization strategies for ELTs (i.e., voting, bagging, boosting and stacking techniques) were tested in a pool of semifinal classification results generated by seven basic classifiers. The high-dimensional neuroimaging features for classification included regional cortical gray matter (GM) thickness and surface area, GM volume of subcortical structures, volume and fractional anisotropy of major white matter fiber tracts, pair-wise regional connectivity and global/nodal topological properties of the functional brain network for cue-evoked attention process. As a result, the bagging-based ELT with the base model of support vector machine achieved the best results, with significant improvement of the area under the receiver of operating characteristic curve (0.89 for ADHD vs. controls and 0.9 for ADHD persisters vs. remitters). Features of nodal efficiency in right inferior frontal gyrus, right middle frontal (MFG)-inferior parietal (IPL) functional connectivity, and right amygdala volume significantly contributed to accurate discrimination between ADHD probands and controls; higher nodal efficiency of right MFG greatly contributed to inattentive and hyperactive/impulsive symptom remission, while higher right MFG-IPL functional connectivity strongly linked to symptom persistence in adults with childhood ADHD. Considering their improved robustness than the commonly implemented basic classifiers, findings suggest that ELTs may have the potential to identify more reliable neurobiological markers for neurodevelopmental disorders.
Summary: Aims: This study aimed at understanding the neurobiological mechanisms associated with inattention induced by traumatic brain injury (TBI). To eliminate the potential confounding caused by the heterogeneity of TBI, we focused on young adults postsports‐related concussion (SRC).Methods: Functional near‐infrared spectroscopy (fNIRS) data were collected from 27 young adults post‐SRC and 27 group‐matched normal controls (NCs), while performing a visual sustained attention task. Task responsive cortical activation maps and pairwise functional connectivity among six regions of interest were constructed for each subject. Correlations among the brain imaging measures and clinical measures of attention were calculated in each group.Results: Compared to the NCs, the SRC group showed significantly increased brain activation in left middle frontal gyrus (MFG) and increased functional connectivity between right inferior occipital cortex (IOC) bilateral calcarine gyri (CG). The left MFG activation magnitude was significantly negatively correlated with the hyperactive/impulsive symptom severity measure in the NCs, but not in the patients. The right hemisphere CG‐IOC functional connectivity showed a significant positive correlation with the hyperactive/impulsive symptom severity measure in patients, but not in NCs.Conclusion: The current data suggest that abnormal left MFG activation and hyper‐communications between right IOC and bilateral CG during visual attention processing may significantly contribute to behavioral manifestations of attention deficits in patients with TBI.