Refine
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- COVID-19 (1)
- Comparative analysis (1)
- Deep neural network (1)
- Gradient boosting (1)
- Multi-syndrome classification (1)
- Neurodegenerative syndromes (1)
- Random forest (1)
- SARS-CoV-2 (1)
- Support vector machine (1)
- neurological manifestations (1)
Institute
- Medizin (4)
Outcomes of SARS-CoV-2 infections in patients with neurodegenerative diseases in the LEOSS cohort
(2021)
The impact of preexisting neurodegenerative diseases on superimposed SARS-CoV-2 infections remains controversial. Here we examined the course and outcome of SARS-CoV-2 infections in patients affected by Parkinson's disease (PD) or dementia compared to matched controls without neurodegenerative diseases in the LEOSS (Lean European Open Survey on SARS-CoV-2-infected patients) cohort, a large-scale prospective multicenter cohort study...
Background and purpose: During acute coronavirus disease 2019 (COVID-19) infection, neurological signs, symptoms and complications occur. We aimed to assess their clinical relevance by evaluating real-world data from a multinational registry. Methods: We analyzed COVID-19 patients from 127 centers, diagnosed between January 2020 and February 2021, and registered in the European multinational LEOSS (Lean European Open Survey on SARS-Infected Patients) registry. The effects of prior neurological diseases and the effect of neurological symptoms on outcome were studied using multivariate logistic regression. Results: A total of 6537 COVID-19 patients (97.7% PCR-confirmed) were analyzed, of whom 92.1% were hospitalized and 14.7% died. Commonly, excessive tiredness (28.0%), headache (18.5%), nausea/emesis (16.6%), muscular weakness (17.0%), impaired sense of smell (9.0%) and taste (12.8%), and delirium (6.7%) were reported. In patients with a complicated or critical disease course (53%) the most frequent neurological complications were ischemic stroke (1.0%) and intracerebral bleeding (ICB; 2.2%). ICB peaked in the critical disease phase (5%) and was associated with the administration of anticoagulation and extracorporeal membrane oxygenation (ECMO). Excessive tiredness (odds ratio [OR] 1.42, 95% confidence interval [CI] 1.20–1.68) and prior neurodegenerative diseases (OR 1.32, 95% CI 1.07–1.63) were associated with an increased risk of an unfavorable outcome. Prior cerebrovascular and neuroimmunological diseases were not associated with an unfavorable short-term outcome of COVID-19. Conclusion: Our data on mostly hospitalized COVID-19 patients show that excessive tiredness or prior neurodegenerative disease at first presentation increase the risk of an unfavorable short-term outcome. ICB in critical COVID-19 was associated with therapeutic interventions, such as anticoagulation and ECMO, and thus may be an indirect complication of a life-threatening systemic viral infection.
Mechanisms behind how the immune system signals to the brain in response to systemic inflammation are not fully understood. Transgenic mice expressing Cre recombinase specifically in the hematopoietic lineage in a Cre reporter background display recombination and marker gene expression in Purkinje neurons. Here we show that reportergene expression in neurons is caused by intercellular transfer of functional Cre recombinase messenger RNA from immune cells into neurons in the absence of cell fusion. In vitro purified secreted extracellular vesicles (EVs) from blood cells contain Cre mRNA, which induces recombination in neurons when injected into the brain. Although Cre-mediated recombination events in the brain occur very rarely in healthy animals, their number increases considerably in different injury models, particularly under inflammatory conditions, and extend beyond Purkinje neurons to other neuronal populations in cortex, hippocampus, and substantia nigra. Recombined Purkinje neurons differ in their miRNA profile from their nonrecombined counterparts, indicating physiological significance. These observations reveal the existence of a previously unrecognized mechanism to communicate RNA-based signals between the hematopoietic system and various organs, including the brain, in response to inflammation.
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.