Associations between attention‐deficit hyperactivity disorder (ADHD) symptom remission and white matter microstructure: A longitudinal analysis

Machine-learning-based feature selection to identify attention-deficit hyperactivity disorder using whole-brain white matter microstructure: A longitudinal study

BACKGROUND

We aimed to identify important features of white matter microstructures collectively distinguishing individuals with attention-deficit/hyperactivity disorder (ADHD) from those without ADHD using a machine-learning approach.

METHODS

Fifty-one ADHD patients and 60 typically developing controls (TDC) underwent diffusion spectrum imaging at two time points. We evaluated three models to classify ADHD and TDC using various machine-learning algorithms. Model 1 employed baseline white matter features of 45 white matter tracts at Time 1; Model 2 incorporated features from both time points; and Model 3 (main analysis) further included the relative rate of change per year of white matter tracts.

RESULTS

The random forest algorithm demonstrated the best performance for classification. Model 1 achieved an area-under-the-curve (AUC) of 0.67. Model 3, incorporating Time 2 variables and relative rate of change per year, improved the performance (AUC = 0.73). In addition to identifying several white matter features at two time points, we found that the relative rate of change per year in the superior longitudinal fasciculus, frontal aslant tract, stria terminalis, inferior fronto-occipital fasciculus, thalamic and striatal tracts, and other tracts involving sensorimotor regions are important features of ADHD. A higher relative change rate in certain tracts was associated with greater improvement in visual attention, spatial short-term memory, and spatial working memory.

CONCLUSIONS

Our findings support the significant diagnostic value of white matter microstructure and the developmental change rates of specific tracts, reflecting deviations from typical development trajectories, in identifying ADHD.

Longitudinal Trajectories of White Matter Development in Attention-Deficit/Hyperactivity Disorder

BACKGROUND

Few longitudinal studies have investigated whether white matter development reflects differential outcomes for children with and without attention-deficit/hyperactivity disorder (ADHD). To examine whether deviations from typical trajectories of white matter development were associated with the persistence or remission of ADHD symptoms, this study examined microstructural and morphological properties of 71 white matter tracts from 390 high angular diffusion scans acquired prospectively for 62 children with persistent ADHD, 37 children remitted from ADHD, and 85 children without ADHD.

METHODS

Participants (mean age at wave 1 = 10.39 years, scan interval = 18 months) underwent up to 3 magnetic resonance imaging assessments. White matter tracts were reconstructed using TractSeg, a semiautomated method. For each tract, we derived measures of fiber density (microstructure) and fiber bundle cross-section (morphology) using fixel-based analysis. Linear mixed models were used to compare trajectories of fiber development between the persistent ADHD, remitted ADHD, and non-ADHD groups.

RESULTS

Compared with the non-ADHD group, the remitted and persistent ADHD groups showed accelerated fiber development in thalamic pathways, striatal pathways, and the superior longitudinal fasciculus. In the remitted ADHD group, accelerated fiber development in corticospinal, frontopontine, striatal-premotor, and thalamo-premotor pathways was associated with greater reductions in ADHD symptom severity. The persistent ADHD group showed ongoing white matter alterations along sensorimotor pathways.

CONCLUSIONS

These results suggest that variations in white matter development are associated with different clinical trajectories in ADHD. The findings advance our understanding of the neurobiological mechanisms underpinning ADHD symptom progression and provide novel evidence in support of developmental models of ADHD.

Atypical development in white matter microstructures in ADHD: A longitudinal diffusion imaging study

BACKGROUND

In cross-sectional studies, alterations in white matter microstructure are evident in children with attention-deficit/hyperactivity disorder (ADHD) but not so prominent in adults with ADHD compared to typically-developing controls (TDC). Moreover, the developmental trajectories of white matter microstructures in ADHD are unclear, given the limited longitudinal imaging studies that characterize developmental changes in ADHD vs. TDC.

METHODS

This longitudinal study acquired diffusion spectrum imaging (DSI) at two time points. The sample included 55 participants with ADHD and 61 TDC. The enrollment/first DSI age ranged from 7 to 18 years, with a five-year mean follow-up time. We examined time-by-diagnosis interaction on the generalized fractional anisotropy (GFA) of 45 white matter tracts, adjusting for confounding factors and correcting for multiple comparisons. We also tested whether the longitudinal changes of microstructures were associated with ADHD symptoms and attention performance in a computerized continuous performance test.

RESULTS

Participants with ADHD showed more rapid development of GFA in the arcuate fasciculus, superior longitudinal fasciculus, frontal aslant tract, cingulum, inferior fronto-occipital fasciculus (IFOF), frontostriatal tract connecting the prefrontal cortex (FS-PFC), thalamic radiation, corticospinal tract, and corpus callosum. Within participants with ADHD, more rapid GFA increases in cingulum and FS-PFC were associated with slower decreases in inattention symptoms. In addition, in all participants, more rapid GFA increases in cingulum and IFOF were associated with greater improvement in attention performance.

CONCLUSION

Our findings suggest atypical developmental trajectories of white matter tracts in ADHD, characterized by normalization and possible compensatory neuroplastic processes with age from childhood to early adulthood.