Refine
Document Type
- Article (3)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- Biomarkers (1)
- Comparative analysis (1)
- Complexin 1 (1)
- Deep neural network (1)
- Gradient boosting (1)
- Multi-syndrome classification (1)
- Neurodegenerative syndromes (1)
- PARK4 (1)
- Parkinson’s disease (1)
- Random forest (1)
- Rapid eye movement sleep behavior disorder (1)
- Support vector machine (1)
- diffusion tensor imaging (1)
- gray matter changes (1)
- restless legs syndrome (1)
- voxel-based morphometry (1)
- white matter changes (1)
- α-synuclein (1)
Institute
- Medizin (3)
- Biowissenschaften (1)
Parkinson's disease (PD) is a frequent neurodegenerative process in old age. Accumulation and aggregation of the lipid-binding SNARE complex component α-synuclein (SNCA) underlies this vulnerability and defines stages of disease progression. Determinants of SNCA levels and mechanisms of SNCA neurotoxicity have been intensely investigated. In view of the physiological roles of SNCA in blood to modulate vesicle release, we studied blood samples from a new large pedigree with SNCA gene duplication (PARK4 mutation) to identify effects of SNCA gain of function as potential disease biomarkers. Downregulation of complexin 1 (CPLX1) mRNA was correlated with genotype, but the expression of other Parkinson's disease genes was not. In global RNA-seq profiling of blood from presymptomatic PARK4 indviduals, bioinformatics detected significant upregulations for platelet activation, hemostasis, lipoproteins, endocytosis, lysosome, cytokine, Toll-like receptor signaling and extracellular pathways. In PARK4 platelets, stimulus-triggered degranulation was impaired. Strong SPP1, GZMH and PLTP mRNA upregulations were validated in PARK4. When analysing individuals with rapid eye movement sleep behavior disorder, the most specific known prodromal stage of general PD, only blood CPLX1 levels were altered. Validation experiments confirmed an inverse mutual regulation of SNCA and CPLX1 mRNA levels. In the 3′-UTR of the CPLX1 gene we identified a single nucleotide polymorphism that is significantly associated with PD risk. In summary, our data define CPLX1 as a PD risk factor and provide functional insights into the role and regulation of blood SNCA levels. The new blood biomarkers of PARK4 in this Turkish family might become useful for PD prediction.
BACKGROUND AND PURPOSE: We evaluated cerebral white and gray matter changes in patients with iRLS in order to shed light on the pathophysiology of this disease.
METHODS: Twelve patients with iRLS were compared to 12 age- and sex-matched controls using whole-head diffusion tensor imaging (DTI) and voxel-based morphometry (VBM) techniques. Evaluation of the DTI scans included the voxelwise analysis of the fractional anisotropy (FA), radial diffusivity (RD), and axial diffusivity (AD).
RESULTS: Diffusion tensor imaging revealed areas of altered FA in subcortical white matter bilaterally, mainly in temporal regions as well as in the right internal capsule, the pons, and the right cerebellum. These changes overlapped with changes in RD. Voxel-based morphometry did not reveal any gray matter alterations.
CONCLUSIONS: We showed altered diffusion properties in several white matter regions in patients with iRLS. White matter changes could mainly be attributed to changes in RD, a parameter thought to reflect altered myelination. Areas with altered white matter microstructure included areas in the internal capsule which include the corticospinal tract to the lower limbs, thereby supporting studies that suggest changes in sensorimotor pathways associated with RLS.
Importance: The entry of artificial intelligence into medicine is pending. Several methods have been used for the predictions of structured neuroimaging data, yet nobody compared them in this context.
Objective: Multi-class prediction is key for building computational aid systems for differential diagnosis. We compared support vector machine, random forest, gradient boosting, and deep feed-forward neural networks for the classification of different neurodegenerative syndromes based on structural magnetic resonance imaging.
Design, setting, and participants: Atlas-based volumetry was performed on multi-centric T1-weighted MRI data from 940 subjects, i.e., 124 healthy controls and 816 patients with ten different neurodegenerative diseases, leading to a multi-diagnostic multi-class classification task with eleven different classes.
Interventions: N.A.
Main outcomes and measures: Cohen’s kappa, accuracy, and F1-score to assess model performance.
Results: Overall, the neural network produced both the best performance measures and the most robust results. The smaller classes however were better classified by either the ensemble learning methods or the support vector machine, while performance measures for small classes were comparatively low, as expected. Diseases with regionally specific and pronounced atrophy patterns were generally better classified than diseases with widespread and rather weak atrophy.
Conclusions and relevance: Our study furthermore underlines the necessity of larger data sets but also calls for a careful consideration of different machine learning methods that can handle the type of data and the classification task best.