Neural correlates of impulse control behaviors in Parkinson's disease: Analysis of multimodal imaging data

Different impulse control disorder evolution patterns and white matter microstructural damage in the progression of Parkinson's disease

Background

The course of impulse control disorders (ICD) varies in the early stage of Parkinson's disease (PD).

Aim

We aimed to delineate the association between the evolution pattern of ICD and the progression of PD.

Methods

A total of 321 de novo PD patients from the Parkinson's Progression Markers Initiative database were included. Patients were followed up for a mean of 6.8 years and were classified into different groups according to the evolution patterns of ICD. Disease progression was compared among groups using survival analysis, in which the endpoint was defined as progression to Hoehn and Yahr stage 3 or higher for motor progression and progression to mild cognitive impairment for cognitive decline. In the fourth year of follow-up, four types of ICD evolution patterns were identified: (1) non-ICD-stable (68.2%), a patient who is consistently free of ICD; (2) late-ICD (14.6%), ICD developed during the follow-up of patients; (3) ICD-stable (11.5%), patients showed persistent ICD; and (4) ICD-reversion (5.6%), baseline ICD disappeared during the follow-up of patients with ICD.

Results

The ICD-reversion type shows daily life non-motor symptoms [Movement Disorder Society-Unified Parkinson Disease Rating Scale (MDS-UPDRS) part I], daily life motor symptoms (MDS-UPDRS part II), rapid eye movement sleep behavior disorder, and anxiety symptoms has a greater impact. PD patients with different ICD evolution patterns had different changes in white matter microstructure at the onset of the disease. Those relevant brain regions are involved in ICD and non-motor functions.

Conclusion

Four early ICD evolution patterns are identified in de novo PD, with different prognoses and brain white matter microstructural damage patterns, and they may predict motor progression and cognitive decline in PD patients.

An Improved Method for Diagnosis of Parkinson's Disease using Deep Learning Models Enhanced with Metaheuristic Algorithm

Accurate diagnosis of Parkinson's disease (PD) at an early stage is challenging for clinicians as its progression is very slow. Currently many machine learning and deep learning approaches are used for detection of PD and they are popular too. This study proposes four deep learning models and a hybrid model for the early detection of PD. Further to improve the performance of the models, grey wolf optimization (GWO) is used to automatically fine-tune the hyperparameters of the models. The simulation study is carried out using two standard datasets, T1,T2-weighted and SPECT DaTscan. The metaherustic enhanced deep learning models used are GWO-VGG16, GWO-DenseNet, GWO-DenseNet + LSTM, GWO-InceptionV3 and GWO-VGG16 + InceptionV3. Simulation results demonstrated that all the models perform well and obtained near above 99% of accuracy. The AUC-ROC score of 99.99 is achieved by the GWO-VGG16 + InceptionV3 and GWO-DenseNet models for T1, T2-weighted dataset. Similarly, the GWO-DenseNet, GWO-InceptionV3 and GWO-VGG16 + InceptionV3 models result an AUC-ROC score of 100 for SPECT DaTscan dataset.

Sleep Traits Causally Affect the Brain Cortical Structure: A Mendelian Randomization Study

Background: Brain imaging results in sleep deprived patients showed structural changes in the cerebral cortex; however, the reasons for this phenomenon need to be further explored. Methods: This MR study evaluated causal associations between morningness, ease of getting up, insomnia, long sleep, short sleep, and the cortex structure. Results: At the functional level, morningness increased the surface area (SA) of cuneus with global weighted (beta(b) (95% CI): 32.63 (10.35, 54.90), p = 0.004). Short sleep increased SA of the lateral occipital with global weighted (b (95% CI): 394.37(107.89, 680.85), p = 0.007. Short sleep reduced cortical thickness (TH) of paracentral with global weighted (OR (95% CI): -0.11 (-0.19, -0.03), p = 0.006). Short sleep reduced TH of parahippocampal with global weighted (b (95% CI): -0.25 (-0.42, -0.07), p = 0.006). No pleiotropy was detected. However, none of the Bonferroni-corrected p values of the causal relationship between cortical structure and the five types of sleep traits met the threshold. Conclusions: Our results potentially show evidence of a higher risk association between neuropsychiatric disorders and not only paracentral and parahippocampal brain areas atrophy, but also an increase in the middle temporal zone. Our findings shed light on the associations of cortical structure with the occurrence of five types of sleep traits.