Refine
Document Type
- Article (3)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
Institute
- Medizin (3)
It has been recognized that molecular classifications will form the basis for neuropathological diagnostic work in the future. Consequently, in order to reach a diagnosis of Alzheimer's disease (AD), the presence of hyperphosphorylated tau (HP-tau) and beta-amyloid protein in brain tissue must be unequivocal. In addition, the stepwise progression of pathology needs to be assessed. This paper deals exclusively with the regional assessment of AD-related HP-tau pathology. The objective was to provide straightforward instructions to aid in the assessment of AD-related immunohistochemically (IHC) detected HP-tau pathology and to test the concordance of assessments made by 25 independent evaluators. The assessment of progression in 7-µm-thick sections was based on assessment of IHC labeled HP-tau immunoreactive neuropil threads (NTs). Our results indicate that good agreement can be reached when the lesions are substantial, i.e., the lesions have reached isocortical structures (stage V–VI absolute agreement 91%), whereas when only mild subtle lesions were present the agreement was poorer (I–II absolute agreement 50%). Thus, in a research setting when the extent of lesions is mild, it is strongly recommended that the assessment of lesions should be carried out by at least two independent observers.
No association between Parkinson disease and autoantibodies against NMDA-type glutamate receptors
(2019)
Background: IgG-class autoantibodies to N-Methyl-D-Aspartate (NMDA)-type glutamate receptors define a novel entity of autoimmune encephalitis. Studies examining the prevalence of NMDA IgA/IgM antibodies in patients with Parkinson disease with/without dementia produced conflicting results. We measured NMDA antibodies in a large, well phenotyped sample of Parkinson patients without and with cognitive impairment (n = 296) and controls (n = 295) free of neuropsychiatric disease. Detailed phenotyping and large numbers allowed statistically meaningful correlation of antibody status with diagnostic subgroups as well as quantitative indicators of disease severity and cognitive impairment.
Methods: NMDA antibodies were analysed in the serum of patients and controls using well established validated assays. We used anti-NMDA antibody positivity as the main independent variable and correlated it with disease status and phenotypic characteristics.
Results: The frequency of NMDA IgA/IgM antibodies was lower in Parkinson patients (13%) than in controls (22%) and higher than in previous studies in both groups. NMDA IgA/IgM antibodies were neither significantly associated with diagnostic subclasses of Parkinson disease according to cognitive impairment, nor with quantitative indicators of disease severity and cognitive impairment. A positive NMDA antibody status was positively correlated with age in controls but not in Parkinson patients.
Conclusion: It is unlikely albeit not impossible that NMDA antibodies play a significant role in the pathogenesis or progression of Parkinson disease e.g. to Parkinson disease with dementia, while NMDA IgG antibodies define a separate disease of its own.
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.