Machine Learning Decomposition of the Anatomy of Neuropsychological Deficit in Alzheimer's Disease and Mild Cognitive Impairment.

Objective: Alzheimer's Disease (AD) is a progressive condition characterized by cognitive decline. AD is often preceded by mild cognitive impairment (MCI), though the diagnosis of both conditions remains a challenge. Early diagnosis of AD, and prediction of MCI progression require data-driven approaches to improve patient selection for treatment. We used a machine learning tool to predict performance in neuropsychological tests in AD and MCI based on functional connectivity using a whole-brain connectome, in an attempt to identify network substrates of cognitive deficits in AD. Methods: Neuropsychological tests, baseline anatomical T1 magnetic resonance imaging (MRI), resting-state functional MRI, and diffusion weighted imaging scans were obtained from 149 MCI, and 85 AD patients; and 140 cognitively unimpaired geriatric participants. A novel machine learning tool, Hollow Tree Super (HoTS) was utilized to extract feature importance from each machine learning model to identify brain regions that were associated with deficit and absence of deficit for 11 neuropsychological tests. Results: 11 models attained an area under the receiver operating curve (AUC-ROC) greater than 0.65, while five models had an AUC-ROC ≥ 0.7. 20 parcels of the Human Connectome Project Multimodal Parcelation Atlas matched to poor performance in at least two neuropsychological tests, while 14 parcels were associated with good performance in at least two tests. At a network level, most parcels predictive of both presence and absence of deficit were affiliated with the Central Executive Network, Default Mode Network, and the Sensorimotor Networks. Segregating predictors by the cognitive domain associated with each test revealed areas of coherent overlap between cognitive domains, with the parcels providing possible markers to screen for cognitive impairment. Conclusion: Approaches such as ours which incorporate whole-brain functional connectivity and harness feature importance in machine learning models may aid in identifying diagnostic and therapeutic targets in AD.

Pediatric Brain Development in Down Syndrome: A Field in Its Infancy.

OBJECTIVES: As surprisingly little is known about the developing brain studied in vivo in youth with Down syndrome (DS), the current review summarizes the small DS pediatric structural neuroimaging literature and begins to contextualize existing research within a developmental framework. METHODS: A systematic review of the literature was completed, effect sizes from published studies were reviewed, and results are presented with respect to the DS cognitive behavioral phenotype and typical brain development. RESULTS: The majority of DS structural neuroimaging studies describe gross differences in brain morphometry and do not use advanced neuroimaging methods to provide nuanced descriptions of the brain. There is evidence for smaller total brain volume (TBV), total gray matter (GM) and white matter, cortical lobar, hippocampal, and cerebellar volumes. When reductions in TBV are accounted for, specific reductions are noted in subregions of the frontal lobe, temporal lobe, cerebellum, and hippocampus. A review of cortical lobar effect sizes reveals mostly large effect sizes from early childhood through adolescence. However, deviance is smaller in adolescence. Despite these smaller effects, frontal GM continues to be largely deviant in adolescence. An examination of age-frontal GM relations using effect sizes from published studies and data from Lee et al. (2016) reveals that while there is a strong inverse relationship between age and frontal GM volume in controls across childhood and adolescence, this is not observed in DS. CONCLUSIONS: Further developmentally focused research, ideally using longitudinal neuroimaging, is needed to elucidate the nature of the DS neuroanatomic phenotype during childhood and adolescence. (JINS, 2018, 24, 966-976).

A conceptual framework for interpreting neuroimaging studies of brain neuroplasticity and cognitive recovery.

Functional neuroimaging technologies are increasingly being used to predict cognitive/behavioral outcomes after the initiation of clinical interventions such as resective surgery or cognitive rehabilitation. We provide a conceptual model and a case example to explain how the results from various neuroimaging techniques can be integrated to answer important questions about clinical recovery such as whether neural reorganization has occurred and, if so, the type of adaptive cognitive mechanism driving this reorganization. This proposed framework and its use in interpreting neuroimaging outcomes studies should help uncover the principles that govern neural reorganization, and be of use to any patient for whom the risk, or potential benefit, of brain-based interventions is unknown.