Machine learning framework to predict pharmacokinetic profile of small molecule drugs based on chemical structure.

Accurate prediction of a new compound's pharmacokinetic (PK) profile is pivotal for the success of drug discovery programs. An initial assessment of PK in preclinical species and humans is typically performed through allometric scaling and mathematical modeling. These methods use parameters estimated from in vitro or in vivo experiments, which although helpful for an initial estimation, require extensive animal experiments. Furthermore, mathematical models are limited by the mechanistic underpinning of the drugs' absorption, distribution, metabolism, and elimination (ADME) which are largely unknown in the early stages of drug discovery. In this work, we propose a novel methodology in which concentration versus time profile of small molecules in rats is directly predicted by machine learning (ML) using structure-driven molecular properties as input and thus mitigating the need for animal experimentation. The proposed framework initially predicts ADME properties based on molecular structure and then uses them as input to a ML model to predict the PK profile. For the compounds tested, our results demonstrate that PK profiles can be adequately predicted using the proposed algorithm, especially for compounds with Tanimoto score greater than 0.5, the average mean absolute percentage error between predicted PK profile and observed PK profile data was found to be less than 150%. The suggested framework aims to facilitate PK predictions and thus support molecular screening and design earlier in the drug discovery process.

Differentiation of multiple system atrophy subtypes by gray matter atrophy.

BACKGROUND AND PURPOSE: Multiple system atrophy(MSA) is a rare adult-onset synucleinopathy that can be divided in two subtypes depending on whether the prevalence of its symptoms is more parkinsonian or cerebellar (MSA-P and MSA-C, respectively). The aim of this work is to investigate the structural MRI changes able to discriminate MSA phenotypes. METHODS: The sample includes 31 MSA patients (15 MSA-C and 16 MSA-P) and 39 healthy controls. Participants underwent a comprehensive motor and neuropsychological battery. MRI data were acquired with a 3T scanner (MAGNETOM Trio, Siemens, Germany). FreeSurfer was used to obtain volumetric and cortical thickness measures. A Support Vector Machine (SVM) algorithm was used to assess the classification between patients' group using cortical and subcortical structural data. RESULTS: After correction for multiple comparisons, MSA-C patients had greater atrophy than MSA-P in the left cerebellum, whereas MSA-P showed reduced volume bilaterally in the pallidum and putamen. Using deep gray matter volume ratios and mean cortical thickness as features, the SVM algorithm provided a consistent classification between MSA-C and MSA-P patients (balanced accuracy 74.2%, specificity 75.0%, and sensitivity 73.3%). The cerebellum, putamen, thalamus, ventral diencephalon, pallidum, and caudate were the most contributing features to the classification decision (z > 3.28; p < .05 [false discovery rate]). CONCLUSIONS: MSA-C and MSA-P with similar disease severity and duration have a differential distribution of gray matter atrophy. Although cerebellar atrophy is a clear differentiator between groups, thalamic and basal ganglia structures are also relevant contributors to distinguishing MSA subtypes.

Impaired Structural Connectivity in Parkinson's Disease Patients with Mild Cognitive Impairment: A Study Based on Probabilistic Tractography.

Background: Probabilistic tractography, in combination with graph theory, has been used to reconstruct the structural whole-brain connectome. Threshold-free network-based statistics (TFNBS) is a useful technique to study structural connectivity in neurodegenerative disorders; however, there are no previous studies using TFNBS in Parkinson's disease (PD) with and without mild cognitive impairment (MCI). Materials and Methods: Sixty-two PD patients, 27 of whom classified as PD-MCI, and 51 healthy controls (HC) underwent diffusion-weighted 3T magnetic resonance imaging. Probabilistic tractography, using FMRIB Software Library (FSL), was used to compute the number of streamlines (NOS) between regions. NOS matrices were used to find group differences with TFNBS, and to calculate global and local measures of network integrity using graph theory. A binominal logistic regression was then used to assess the discrimination between PD with and without MCI using non-overlapping significant tracts. Tract-based spatial statistics were also performed with FSL to study changes in fractional anisotropy (FA) and mean diffusivity. Results: PD-MCI showed 37 white matter connections with reduced connectivity strength compared with HC, mainly involving temporal/occipital regions. These were able to differentiate PD-MCI from PD without MCI with an area under the curve of 83-85%. PD without MCI showed disrupted connectivity in 18 connections involving frontal/temporal regions. No significant differences were found in graph measures. Only PD-MCI showed reduced FA compared with HC. Discussion: TFNBS based on whole-brain probabilistic tractography can detect structural connectivity alterations in PD with and without MCI. Reduced structural connectivity in fronto-striatal and posterior cortico-cortical connections is associated with PD-MCI.

Inferring pain experience in infants using quantitative whole-brain functional MRI signatures: a cross-sectional, observational study.

Background: In the absence of verbal communication, it is challenging to infer an individual's sensory and emotional experience. In communicative adults, functional MRI (fMRI) has been used to develop multivariate brain activity signatures, which reliably capture elements of human pain experience. We aimed to translate whole-brain fMRI signatures that encode pain perception in adults to the newborn infant brain, to advance understanding of functional brain development and pain perception in early life. Methods: In this cross-sectional, observational study, we recruited adults at the University of Oxford (Oxford, UK) and infants on the postnatal wards of John Radcliffe Hospital (Oxford, UK). Healthy full-term infants were eligible for inclusion if they were clinically stable, self-ventilating in air, and had no neurological abnormalities. Infants were consecutively recruited in two cohorts (A and B) due to the installation of a new fMRI scanner using the same recruitment criteria. Adults (aged ≥18 years) were eligible if they were postgraduate students or staff at the University of Oxford. Participants were stimulated with low intensity nociceptive stimuli (64, 128, 256, and 512 mN in adults; 64 and 128 mN in infants) during acquisition of fMRI data. fMRI pain signatures (neurologic pain signature [NPS] and stimulus intensity independent pain signature-1 [SIIPS1]), and four control signatures (the vicarious pain signature, the picture-induced negative emotion signature [PINES], the social rejection signature, and a global signal signature) were applied directly to the adult data and translated to the infant brain. We assessed the concordance of the signatures with the brain responses of adults and infants using cosine similarity scores, and we assessed stimulus intensity encoding of the signature responses using a Spearman rank correlation test. We also assessed brain activity in pro-pain and anti-pain components of the signatures. Findings: Between May 22, 2013, and Jan 29, 2018, we recruited ten healthy participants to the adult cohort (five women and five men; mean age 28·3 years [range 23-36]), 15 infants to infant cohort A (six girls and nine boys; mean postnatal age 4 days [range 1-11]), and 22 infants to infant cohort B (11 girls and 11 boys; mean postnatal age 3 days [range 1-10]). The NPS was activated in both the adults and infants, and reliably encoded stimulus intensity. The NPS was activated in the adult cohort (p<0·0001) and both infant cohorts (p=0·048 for infant cohort A; p=0·001 for infant cohort B). The SIIPS1 was only expressed in adults. Pro-pain brain regions showed similar activation patterns in adults and infants, whereas responses in anti-pain brain regions were divergent. Interpretation: Basic intensity encoding of nociceptive information is similar in adults and infants. However, translation of adult brain signatures to infants indicated substantial differences in infant cerebral processing of nociceptive information, which might reflect their absence of expectation, motivation, and contextualisation associated with pain. This study expands the use of brain activity pain signatures to non-verbal patients and provides a potential research approach to assess the impact of analgesic interventions on brain function in infants. Funding: Wellcome Trust, Supporting the Sick Newborn and their Parents Medical Research Fund.

Data for functional MRI connectivity in transgender people with gender incongruence and cisgender individuals.

We provide T2*-weighted and T1-weighted images acquired on a 3T MRI scanner obtained from 17 transwomen and 29 transmen with gender incongruence; and 22 ciswomen and 19 cismen that identified themselves to the sex assigned at birth. Data from three different techniques that describe global and regional connectivity differences within functional resting-state networks in transwomen and transmen with early-in-life onset gender incongruence are provided: (1) we obtained spatial maps from data-driven independent component analysis using the melodic tool from FSL software; (2) we provide the functional networks interactions of two functional atlases' seeds from a seed-to-seed approach; (3) and global graph-theoretical metrics such as the smallworld organization, and the segregation and integration properties of the networks. Interpretations of the present dataset can be found in the original article, doi:10.1016/j.neuroimage.2020.116613[1]. The original and processed nifti images are available in Mendeley datasets. In addition, correlation matrices for the seed-to-seed and graph-theory analyses as well as the graph-theoretical measures were made available in Matlab files. Finally, we present supplementary information for the original article.

Brain network interactions in transgender individuals with gender incongruence.

Functional brain organization in transgender persons remains unclear. Our aims were to investigate global and regional connectivity differences within functional networks in transwomen and transmen with early-in-life onset gender incongruence; and to test the consistency of two available hypotheses that attempted to explain gender variants: (i) a neurodevelopmental cortical hypothesis that suggests the existence of different brain phenotypes based on structural MRI data and genes polymorphisms of sex hormone receptors; (ii) a functional-based hypothesis in relation to regions involved in the own body perception. T2*-weighted images in a 3-T MRI were obtained from 29 transmen and 17 transwomen as well as 22 cisgender women and 19 cisgender men. Resting-state independent component analysis, seed-to-seed functional network and graph theory analyses were performed. Transmen, transwomen, and cisgender women had decreased connectivity compared with cisgender men in superior parietal regions, as part of the salience (SN) and the executive control (ECN) networks. Transmen also had weaker connectivity compared with cisgender men between intra-SN regions and weaker inter-network connectivity between regions of the SN, the default mode network (DMN), the ECN and the sensorimotor network. Transwomen had lower small-worldness, modularity and clustering coefficient than cisgender men. There were no differences among transmen, transwomen, and ciswomen. Together these results underline the importance of the SN interacting with DMN, ECN, and sensorimotor networks in transmen, involving regions of the entire brain with a frontal predominance. Reduced global connectivity graph-theoretical measures were a characteristic of transwomen. It is proposed that the interaction between networks is a keystone in building a gendered self. Finally, our findings suggest that both proposed hypotheses are complementary in explaining brain differences between gender variants.

Differentiation of multiple system atrophy from Parkinson's disease by structural connectivity derived from probabilistic tractography.

Recent studies combining diffusion tensor-derived metrics and machine learning have shown promising results in the discrimination of multiple system atrophy (MSA) and Parkinson's disease (PD) patients. This approach has not been tested using more complex methodologies such as probabilistic tractography. The aim of this work is assessing whether the strength of structural connectivity between subcortical structures, measured as the number of streamlines (NOS) derived from tractography, can be used to classify MSA and PD patients at the single-patient level. The classification performance of subcortical FA and MD was also evaluated to compare the discriminant ability between diffusion tensor-derived metrics and NOS. Using diffusion-weighted images acquired in a 3 T MRI scanner and probabilistic tractography, we reconstructed the white matter tracts between 18 subcortical structures from a sample of 54 healthy controls, 31 MSA patients and 65 PD patients. NOS between subcortical structures were compared between groups and entered as features into a machine learning algorithm. Reduced NOS in MSA compared with controls and PD were found in connections between the putamen, pallidum, ventral diencephalon, thalamus, and cerebellum, in both right and left hemispheres. The classification procedure achieved an overall accuracy of 78%, with 71% of the MSA subjects and 86% of the PD patients correctly classified. NOS features outperformed the discrimination performance obtained with FA and MD. Our findings suggest that structural connectivity derived from tractography has the potential to correctly distinguish between MSA and PD patients. Furthermore, NOS measures obtained from tractography might be more useful than diffusion tensor-derived metrics for the detection of MSA.

Disrupted structural connectivity of fronto-deep gray matter pathways in progressive supranuclear palsy.

BACKGROUND: Structural connectivity is a promising methodology to detect patterns of neural network dysfunction in neurodegenerative diseases. This approach has not been tested in progressive supranuclear palsy (PSP). OBJECTIVES: The aim of this study is reconstructing the structural connectome to characterize and detect the pathways of degeneration in PSP patients compared with healthy controls and their correlation with clinical features. The second objective is to assess the potential of structural connectivity measures to distinguish between PSP patients and healthy controls at the single-subject level. METHODS: Twenty healthy controls and 19 PSP patients underwent diffusion-weighted MRI with a 3T scanner. Structural connectivity, represented by number of streamlines, was derived from probabilistic tractography. Global and local network metrics were calculated based on graph theory. RESULTS: Reduced numbers of streamlines were predominantly found in connections between frontal areas and deep gray matter (DGM) structures in PSP compared with controls. Significant changes in structural connectivity correlated with clinical features in PSP patients. An abnormal small-world architecture was detected in the subnetwork comprising the frontal lobe and DGM structures in PSP patients. The classification procedure achieved an overall accuracy of 82.23% with 94.74% sensitivity and 70% specificity. CONCLUSION: Our findings suggest that modelling the brain as a structural connectome is a useful method to detect changes in the organization and topology of white matter tracts in PSP patients. Secondly, measures of structural connectivity have the potential to correctly discriminate between PSP patients and healthy controls.

Neuroanatomical and Functional Correlates of Cognitive and Affective Empathy in Young Healthy Adults.

Neural substrates of empathy are mainly investigated through task-related functional MRI. However, the functional neural mechanisms at rest underlying the empathic response have been poorly studied. We aimed to investigate neuroanatomical and functional substrates of cognitive and affective empathy. The self-reported empathy questionnaire Cognitive and Affective Empathy Test (TECA), T1 and T2∗-weighted 3-Tesla MRI were obtained from 22 healthy young females (mean age: 19.6 ± 2.4) and 20 males (mean age: 22.5 ± 4.4). Groups of low and high empathy were established for each scale. FreeSurfer v6.0 was used to estimate cortical thickness and to automatically segment the subcortical structures. FSL v5.0.10 was used to compare resting-state connectivity differences between empathy groups in six defined regions: the orbitofrontal, cingulate, and insular cortices, and the amygdala, hippocampus, and thalamus using a non-parametric permutation approach. The high empathy group in the Perspective Taking subscale (cognitive empathy) had greater thickness in the left orbitofrontal and ventrolateral frontal cortices, bilateral anterior cingulate, superior frontal, and occipital regions. Within the affective empathy scales, subjects with high Empathic Distress had higher thalamic volumes than the low-empathy group. Regarding resting-state connectivity analyses, low-empathy individuals in the Empathic Happiness scale had increased connectivity between the orbitofrontal cortex and the anterior cingulate when compared with the high-empathy group. In conclusion, from a structural point of view, there is a clear dissociation between the brain correlates of affective and cognitive factors of empathy. Neocortical correlates were found for the cognitive empathy dimension, whereas affective empathy is related to lower volumes in subcortical structures. Functionally, affective empathy is linked to connectivity between the orbital and cingulate cortices.

Progression of Parkinson's disease patients' subtypes based on cortical thinning: 4-year follow-up.

BACKGROUND: Three cortical atrophy patterns were previously identified in non-demented Parkinson's disease patients using a data-driven approach based on cortical thickness data: i) parieto-temporal pattern of atrophy with worse cognitive performance (pattern 1), ii) occipital and frontal cortical atrophy with younger disease onset (pattern 2), and iii) non-detectable cortical atrophy (pattern 3). We aimed to investigate the evolution of these three patterns over time. METHODS: Magnetic resonance imaging and neuropsychological assessment were obtained at baseline and follow-up (3.8 ±â€¯0.4 year apart) in a group of 45 Parkinson's disease patients and 22 healthy controls. FreeSurfer was used for cortical thickness analysis and global atrophy measures. RESULTS: Temporo-parietal cortical thinning occurred in pattern 2, 3 and controls groups, and patients showed decline in processing speed (as measured by the Stroop Word-Color test, the Symbol Digits Modalities test and the Trail Making Test Part B) and in semantic fluency (animals). Pattern 3 patients showed more progressive cortical thinning in the left prefrontal cortex than controls and more right occipital thinning than pattern 2 patients over time. Pattern 1 patients had greater compromise in activities of the daily living and suffered higher attrition rate. CONCLUSION: The Parkinson's disease phenotypes identified using cluster analysis of cortical thickness data showed different progression over time. The presence of prefrontal thinning and younger disease onset at baseline was associated to less cortical degeneration, while non-atrophic patients progressed showing a temporo-parietal cortical thinning.

Cortical Gray Matter and Hippocampal Atrophy in Idiopathic Rapid Eye Movement Sleep Behavior Disorder.

Objective: In this study we investigate cortical and subcortical gray matter structure in patients with Idiopathic REM-sleep behavior disorder (IRBD), and their relation to cognitive performance. Methods: This study includes a sample of 20 patients with polysomnography-confirmed IRBD and 27 healthy controls that underwent neuropsychological and T1-weighted MRI assessment. FreeSurfer was used to estimate cortical thickness, subcortical volumetry (version 5.1), and hippocampal subfields segmentation (version 6.0). FIRST, FSL's model-based segmentation/registration tool was used for hippocampal shape analysis. Results: Compared with healthy subjects, IRBD patients showed impairment in facial recognition, verbal memory, processing speed, attention, and verbal naming. IRBD patients had cortical thinning in left superior parietal, post-central, and fusiform regions, as well as in right superior frontal and lateral occipital regions. Volumetric and shape analyses found right hippocampal atrophy in IRBD, specifically in posterior regions. Hippocampal subfields exploratory analysis identified significant differences in the right CA1, molecular layer, granule cell layer of dentate gyrus, and CA4 of this patients. No correlations were found between cognitive performance and brain atrophy. Conclusion: This work confirms the presence of posterior based cognitive dysfunction, as well as cortical and right hippocampal atrophy in IRBD patients.

Cerebellar resting-state functional connectivity in Parkinson's disease and multiple system atrophy: Characterization of abnormalities and potential for differential diagnosis at the single-patient level.

BACKGROUND: Recent studies using resting-state functional connectivity and machine-learning to distinguish patients with neurodegenerative diseases from other groups of subjects show promising results. This approach has not been tested to discriminate between Parkinson's disease (PD) and multiple system atrophy (MSA) patients. OBJECTIVES: Our first aim is to characterize possible abnormalities in resting-state functional connectivity between the cerebellum and a set of intrinsic-connectivity brain networks and between the cerebellum and different regions of the striatum in PD and MSA. The second objective of this study is to assess the potential of cerebellar connectivity measures to distinguish between PD and MSA patients at the single-patient level. METHODS: Fifty-nine healthy controls, 62 PD patients, and 30 MSA patients underwent resting-state functional MRI with a 3T scanner. Independent component analysis and dual regression were used to define seven resting-state networks of interest. To assess striatal connectivity, a seed-to-voxel approach was used after dividing the striatum into six regions bilaterally. Measures of cerebellar-brain network and cerebellar-striatal connectivity were then used as features in a support vector machine to discriminate between PD and MSA patients. RESULTS: MSA patients displayed reduced cerebellar connectivity with different brain networks and with the striatum compared with PD patients and with controls. The classification procedure achieved an overall accuracy of 77.17% with 83.33% of the MSA subjects and 74.19% of the PD patients correctly classified. CONCLUSION: Our findings suggest that measures of cerebellar functional connectivity have the potential to distinguish between PD and MSA patients.

Differential Progression of Regional Hippocampal Atrophy in Aging and Parkinson's Disease.

Hippocampal subfields have different vulnerability to the degenerative processes related to aging, amnestic mild cognitive impairment (MCI) and Alzheimer's disease (AD), but the temporal evolution in Parkinson's disease (PD) is unknown. The purposes of the current work are to describe regional hippocampal changes over time in a sample of PD patients classified according to their baseline cognitive status and to relate these changes to verbal memory loss. T1-weighted images and verbal memory assessment were obtained at two separate time points (3.8 ± 0.4 years apart) from 28 PD with normal cognition (PD-NC), 16 PD with MCI (PD-MCI) and 21 healthy controls (HCs). FreeSurfer 6.0 automated pipeline was used to segment the hippocampus into 12 bilateral subregions. Memory functions were measured with Rey's Auditory Verbal learning test (RAVLT). We found significant reductions in cornu ammonis 1 (CA1) over time in controls as well as in PD subgroups. Right whole-hippocampal volumes showed time effects in both PD groups but not in controls. PD-NC patients also displayed time effects in the left hippocampal tail and right parasubiculum. Regression analyses showed that specific hippocampal subfield volumes at time 1 predicted almost 60% of the variability in RAVLT delayed-recall score decline. Changes in several hippocampal subregions also showed predictive value for memory loss. In conclusion, CA1 changes in PD were similar to those that occur in normal aging, but PD patients also had more decline in both anterior and posterior hippocampal segments with a more pronounced atrophy of the right hemisphere. Hippocampal segments are better predictors of changes in memory performance than whole-hippocampal volumes.

Gray/White Matter Contrast in Parkinson's Disease.

Gray/white matter contrast (GWC) decreases with aging and has been found to be a useful MRI biomarker in Alzheimer's disease (AD), but its utility in Parkinson's disease (PD) patients has not been investigated. The aims of the study were to test whether GWC is sensitive to aging changes in PD patients, if PD patients differ from healthy controls (HCs) in GWC, and whether the use of GWC data would improve the sensitivity of cortical thickness analyses to differentiate PD patients from controls. Using T1-weighted structural images, we obtained individual cortical thickness and GWC values from a sample of 90 PD patients and 27 controls. Images were processed with the automated FreeSurfer stream. GWC was computed by dividing the white matter (WM) by the gray matter (GM) values and projecting the ratios onto a common surface. The sample characteristics were: 52 patients and 14 controls were males; mean age of 64.4 ± 10.6 years in PD and 64.7 ± 8.6 years in controls; 8.0 ± 5.6 years of disease evolution; 15.6 ± 9.8 UPDRS; and a range of 1.5-3 in Hoehn and Yahr (H&Y) stage. In both PD and controls we observed significant correlations between GWC and age involving almost the entire cortex. When applying a stringent cluster-forming threshold of p < 0.0001, the correlation between GWC and age also involved the entire cortex in the PD group; in the control group, the correlation was found in the parahippocampal gyrus and widespread frontal and parietal areas. The GWC of PD patients did not differ from controls', whereas cortical thickness analyses showed thinning in temporal and parietal cortices in the PD group. Cortical thinning remained unchanged after adjusting for GWC. GWC is a very sensitive measure for detecting aging effects, but did not provide additional information over other parameters of atrophy in PD.

Statistical inference in brain graphs using threshold-free network-based statistics.

The description of brain networks as graphs where nodes represent different brain regions and edges represent a measure of connectivity between a pair of nodes is an increasingly used approach in neuroimaging research. The development of powerful methods for edge-wise group-level statistical inference in brain graphs while controlling for multiple-testing associated false-positive rates, however, remains a difficult task. In this study, we use simulated data to assess the properties of threshold-free network-based statistics (TFNBS). The TFNBS combines threshold-free cluster enhancement, a method commonly used in voxel-wise statistical inference, and network-based statistic (NBS), which is frequently used for statistical analysis of brain graphs. Unlike the NBS, TFNBS generates edge-wise significance values and does not require the a priori definition of a hard cluster-defining threshold. Other test parameters, nonetheless, need to be set. We show that it is possible to find parameters that make TFNBS sensitive to strong and topologically clustered effects, while appropriately controlling false-positive rates. Our results show that the TFNBS is an adequate technique for the statistical assessment of brain graphs.

Cortical atrophy patterns in early Parkinson's disease patients using hierarchical cluster analysis.

INTRODUCTION: Cortical brain atrophy detectable with MRI in non-demented advanced Parkinson's disease (PD) is well characterized, but its presence in early disease stages is still under debate. We aimed to investigate cortical atrophy patterns in a large sample of early untreated PD patients using a hypothesis-free data-driven approach. METHODS: Seventy-seven de novo PD patients and 50 controls from the Parkinson's Progression Marker Initiative database with T1-weighted images in a 3-tesla Siemens scanner were included in this study. Mean cortical thickness was extracted from 360 cortical areas defined by the Human Connectome Project Multi-Modal Parcellation version 1.0, and a hierarchical cluster analysis was performed using Ward's linkage method. A general linear model with cortical thickness data was then used to compare clustering groups using FreeSurfer software. RESULTS: We identified two patterns of cortical atrophy. Compared with controls, patients grouped in pattern 1 (n = 33) were characterized by cortical thinning in bilateral orbitofrontal, anterior cingulate, and lateral and medial anterior temporal gyri. Patients in pattern 2 (n = 44) showed cortical thinning in bilateral occipital gyrus, cuneus, superior parietal gyrus, and left postcentral gyrus, and they showed neuropsychological impairment in memory and other cognitive domains. CONCLUSIONS: Even in the early stages of PD, there is evidence of cortical brain atrophy. Neuroimaging clustering analysis is able to detect two subgroups of cortical thinning, one with mainly anterior atrophy, and the other with posterior predominance and worse cognitive performance.

Structural Brain Correlations of Visuospatial and Visuoperceptual Tests in Parkinson's Disease.

BACKGROUND: Diagnosis of mild cognitive impairment in Parkinson's disease (PD) is relevant because it is a marker for evolution to dementia. However, the selection of suitable tests to evaluate separate cognitive domains in mild cognitive impairment related to PD remains an open question. The current work aims to investigate the neuroanatomical correlates of several visuospatial/visuoperceptual tests using the same sample and a multimodal MRI approach. METHODS: The study included 36 PD patients and 20 healthy subjects matched for age, sex, and education. The visuospatial/visuoperceptual tests selected were: Pentagon Copying Test (PCT), Judgment of Line Orientation Test (JLOT), Visual Form Discrimination Test (VFDT), Facial Recognition Test (FRT), Symbol Digit Modalities Test (SMDT), and clock copying task (CLOX2). FreeSurfer was used to assess cortical thickness, and tract-based spatial statistics was used for fractional anisotropy analysis. RESULTS: Lower performance in the PCT, JLOT, and SDMT was associated with extensive cortical thickness reductions in lateral parietal and temporal regions. VFDT and CLOX2 did not show this common pattern and correlated with more limited medial occipito-temporal and occipito-parietal regions. Performance in all visuospatial/visuoperceptual tests correlated with fractional anisotropy in the corpus callosum. CONCLUSIONS: Our findings show that JLOT, SDMT, and PCT, in addition to differentiating patients from controls, are suitable visuospatial/visuoperceptual tests to reflect cortical thinning in lateral temporo-parietal regions in PD patients. We did not observe the dissociation between dorsal and ventral streams that was expected according to the neuropsychological classification of visuospatial and visuoperceptual tests. (JINS, 2018, 24, 33-44).

Brain correlates of progressive olfactory loss in Parkinson's disease.

BACKGROUND: Olfactory dysfunction is present in a large proportion of patients with Parkinson's disease (PD) upon diagnosis. However, its progression over time has been poorly investigated. The few available longitudinal studies lack control groups or MRI data. OBJECTIVE: To investigate the olfactory changes and their structural correlates in non-demented PD over a four-year follow-up. METHODS: We assessed olfactory function in a sample of 25 PD patients and 24 normal controls of similar age using the University of Pennsylvania Smell Identification test (UPSIT). Structural magnetic resonance imaging data, obtained with a 3-T Siemens Trio scanner, were analyzed using FreeSurfer software. RESULTS: Analysis of variance showed significant group (F = 53.882; P < 0.001) and time (F = 6.203; P = 0.016) effects, but the group-by-time interaction was not statistically significant. UPSIT performance declined ≥1.5 standard deviations in 5 controls and 7 patients. Change in UPSIT scores of patients correlated positively with volume change in the left putamen, right thalamus, and right caudate nucleus. CONCLUSION: Olfactory loss over time in PD and controls is similar, but we have observed significant correlation between this loss and basal ganglia volumes only in patients.

Discriminating cognitive status in Parkinson's disease through functional connectomics and machine learning.

There is growing interest in the potential of neuroimaging to help develop non-invasive biomarkers in neurodegenerative diseases. In this study, connection-wise patterns of functional connectivity were used to distinguish Parkinson's disease patients according to cognitive status using machine learning. Two independent subject samples were assessed with resting-state fMRI. The first (training) sample comprised 38 healthy controls and 70 Parkinson's disease patients (27 with mild cognitive impairment). The second (validation) sample included 25 patients (8 with mild cognitive impairment). The Brainnetome atlas was used to reconstruct the functional connectomes. Using a support vector machine trained on features selected through randomized logistic regression with leave-one-out cross-validation, a mean accuracy of 82.6% (p < 0.002) was achieved in separating patients with mild cognitive impairment from those without it in the training sample. The model trained on the whole training sample achieved an accuracy of 80.0% when used to classify the validation sample (p = 0.006). Correlation analyses showed that the connectivity level in the edges most consistently selected as features was associated with memory and executive function performance in the patient group. Our results demonstrate that connection-wise patterns of functional connectivity may be useful for discriminating Parkinson's disease patients according to the presence of cognitive deficits.

Patterns of cortical thinning in nondemented Parkinson's disease patients.

BACKGROUND: Clinical variability in the Parkinson's disease phenotype suggests the existence of disease subtypes. We investigated whether distinct anatomical patterns of atrophy can be identified in Parkinson's disease using a hypothesis-free, data-driven approach based on cortical thickness data. METHODS: T1-weighted 3-tesla MRI and a comprehensive neuropsychological assessment were performed in a sample of 88 nondemented Parkinson's disease patients and 31 healthy controls. We performed a hierarchical cluster analysis of imaging data using Ward's linkage method. A general linear model with cortical thickness data was used to compare clustering groups. RESULTS: We observed 3 patterns of cortical thinning in patients when compared with healthy controls. Pattern 1 (n = 30, 34.09%) consisted of cortical atrophy in bilateral precentral gyrus, inferior and superior parietal lobules, cuneus, posterior cingulate, and parahippocampal gyrus. These patients showed worse cognitive performance when compared with controls and the other 2 patterns. Pattern 2 (n = 29, 32.95%) consisted of cortical atrophy involving occipital and frontal as well as superior parietal areas and included patients with younger age at onset. Finally, in pattern 3 (n = 29, 32.95%), there was no detectable cortical thinning. Patients in the 3 patterns did not differ in disease duration, motor severity, dopaminergic medication doses, or presence of mild cognitive impairment. CONCLUSIONS: Three cortical atrophy subtypes were identified in nondemented Parkinson's disease patients: (1) parieto-temporal pattern of atrophy with worse cognitive performance, (2) occipital and frontal cortical atrophy and younger disease onset, and (3) patients without detectable cortical atrophy. These findings may help identify prognosis markers in Parkinson's disease. © 2016 The Authors. Movement Disorders published by Wiley Periodicals, Inc. on behalf of International Parkinson and Movement Disorder Society.