Cortical Thickness from MRI to Predict Conversion from Mild Cognitive Impairment to Dementia in Parkinson Disease: A Machine Learning-based Model.

Background Group comparison results associating cortical thinning and Parkinson disease (PD) dementia (PDD) are limited in their application to clinical settings. Purpose To investigate whether cortical thickness from MRI can help predict conversion from mild cognitive impairment (MCI) to dementia in PD at an individual level using a machine learning-based model. Materials and Methods In this retrospective study, patients with PD and MCI who underwent MRI from September 2008 to November 2016 were included. Features were selected from clinical and cortical thickness variables in 10 000 randomly generated training sets. Features selected 5000 times or more were used to train random forest and support vector machine models. Each model was trained and tested in 10 000 randomly resampled data sets, and a median of 10 000 areas under the receiver operating characteristic curve (AUCs) was calculated for each. Model performances were validated in an external test set. Results Forty-two patients progressed to PDD (converters) (mean age, 71 years ± 6 [standard deviation]; 22 women), and 75 patients did not progress to PDD (nonconverters) (mean age, 68 years ± 6; 40 women). Four PDD converters (mean age, 74 years ± 10; four men) and 20 nonconverters (mean age, 67 years ± 7; 11 women) were included in the external test set. Models trained with cortical thickness variables (AUC range, 0.75-0.83) showed fair to good performances similar to those trained with clinical variables (AUC range, 0.70-0.81). Model performances improved when models were trained with both variables (AUC range, 0.80-0.88). In pair-wise comparisons, models trained with both variables more frequently showed better performance than others in all model types. The models trained with both variables were successfully validated in the external test set (AUC range, 0.69-0.84). Conclusion Cortical thickness from MRI helped predict conversion from mild cognitive impairment to dementia in Parkinson disease at an individual level, with improved performance when integrated with clinical variables. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Port in this issue.

Neural and dopaminergic correlates of fatigue in Parkinson's disease.

Fatigue is one of the most common non-motor symptoms in Parkinson's disease (PD). Despite its clinical importance, there are few studies on the cause or mechanism of fatigue. Our aim was to find brain areas related to fatigue and to explore the association between striatal dopaminergic dysfunction and fatigue. We consecutively screened forty-seven patients with de novo PD from 2012 to 2017 and enrolled 32 patients. The gray matter volumes, white matter tracts, and striatal dopaminergic activity between PD without fatigue and with fatigue were compared. The correlation between fatigue and striatal dopaminergic activity was also analyzed. Our data did not show any significant difference in gray matter volume between PD without fatigue and with fatigue (familywise error [FWE] corrected p > 0.05) but revealed significantly higher mean fractional anisotropy (FA) values for all analyzed white matter tracts in PD with fatigue (false discovery rate [FDR] corrected p < 0.05), except left cingulum-hippocampus (CH), right superior longitudinal fasciculus, and right longitudinal fasciculus temporal part (FDR corrected p > 0.06); lower mean diffusivity (MD) values for all analyzed white matter tracts in PD with fatigue (FDR corrected p < 0.05), except in the left CH and uncinate fasciculus (FDR corrected p > 0.05). The mean radial diffusivity (RD) values, except for the left CH (FDR corrected p = 0.0576), were also significantly lower (FDR corrected p < 0.05). There was no difference in dopaminergic deficits between PD without fatigue and PD with fatigue (p > 0.50). The alteration of the white matter tract may reflect the degree of fatigue in PD. This is not true of the gray matter and striatal dopaminergic activity. These results show the possibility that white matter changes can be used as a biomarker for fatigue.

Sleep disturbance-related depressive symptom and brain volume reduction in shift-working nurses.

Disturbed sleep is the most common effect of shift work. A large corpus of research indicates an association between sleep disturbance and depressive symptom in shift workers. In this study, we proposed the mediating role of grey matter (GM) structure in the relationship between sleep disturbance and depressive symptom. We collected structural MRI (sMRI) data as well as assessing the level of sleep disturbance and depressive symptom with the Pittsburgh Sleep disturbance Index and Zung Self-Rating Depression Scale, respectively, in 20 shift-working nurses and 19 day-working nurses. The shift-working nurses reported greater severity of sleep disturbance and depressive symptom, and furthermore, they exhibited reduced GM volume in the left postcentral gyrus (PostCG), right PostCG, right paracentral lobule, and left superior temporal gyrus (STG), compared to the day-working nurses. For each of the four brain regions, we formulated a mediation hypothesis by developing a mediation model that represents a causal chain between GM volume, sleep disturbance, and depressive symptom. Tests of the hypothesis on the mediation of GM volume revealed that inter-individual variations in left PostCG volume and left STG volume accounted for the influence of sleep disturbance on depressive symptom. These results suggest that structural alterations in PostCG and STG play an intervening role in the development of depressive symptom following sleep disturbance. We propose the need of considering neuroanatomical abnormalities in explaining and understanding symptomatic changes induced by sleep disturbance.

Blood pressure lability is associated with subcortical atrophy in early Parkinson's disease.

OBJECTIVE: Increased cerebral white matter intensities associated with blood pressure (BP) lability were reported in patients with Parkinson's disease. However, this type of cardiovascular dysautonomia has seldom been associated with disruptions in deep gray matter structures in Parkinson's disease. In the present study, the associations between BP lability and subcortical deep gray matter structures in early Parkinson's disease were evaluated. METHODS: The present study included 98 early nondemented Parkinson's disease patients. Supine and orthostatic BPs were measured using head-up tilt tests. BP variabilities, measured as standard deviations of 24-h daytime and nighttime BPs, were assessed using 24-h ambulatory BP monitoring. Every patient underwent brain MRI and measurement of deep gray matter volumes. The associations between BP lability and deep gray matter structures were analyzed. RESULTS: Parkinson's disease patients with orthostatic hypotension had smaller volumes of striatum, particularly caudate, than patients without OH after adjusting for covariates of age, sex, disease duration, and Mini-Mental Status Examination score. Nocturnal BP variability was inversely associated with thalamus, hippocampus, and globus pallidus volumes. CONCLUSION: The results from the present study showed that BP lability was adversely associated with structural changes in early Parkinson's disease. Different forms of BP fluctuations influenced distinct deep gray matter structures.