Refine
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
Institute
- Medizin (2)
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.
Highligthts
• Marburg virus infects and replicates in primary human proximal tubular cells (PTC).
• Transcriptome analyses at multiple time points revealed a profound inflammatory response by IFNα, -y and TNFα signaling.
• Among the strongly downregulated gene sets were targets of the transcription factors MYC and E2F, the G2M checkpoint, as well as oxidative phosphorylation.
• Importantly, the downregulated factors comprise PGC-1α, a key factor in mitochondrial biogenesis and renal energy homeostasis, to be substantially downregulated in MARV-infected PTC.
• Our results suggest inflammation-induced changes in tubular energy metabolism as a possible factor in MARV-associated tubular dysfunction.
Abstract
Marburg virus, a member of the Filoviridae, is the causative agent of Marburg virus disease (MVD), a hemorrhagic fever with a case fatality rate of up to 90 %. Acute kidney injury is common in MVD and is associated with increased mortality, but its pathogenesis in MVD remains poorly understood. Interestingly, autopsies show the presence of viral proteins in different parts of the nephron, particularly in proximal tubular cells (PTC). These findings suggest a potential role for the virus in the development of MVD-related kidney injury. To shed light on this effect, we infected primary human PTC with Lake Victoria Marburg virus and conducted transcriptomic analysis at multiple time points. Unexpectedly, infection did not induce marked cytopathic effects in primary tubular cells at 20 and 40 h post infection. However, gene expression analysis revealed robust renal viral replication and dysregulation of genes essential for different cellular functions. The gene sets mainly downregulated in PTC were associated with the targets of the transcription factors MYC and E2F, DNA repair, the G2M checkpoint, as well as oxidative phosphorylation. Importantly, the downregulated factors comprise PGC-1α, a well-known factor in acute and chronic kidney injury. By contrast, the most highly upregulated gene sets were those related to the inflammatory response and cholesterol homeostasis. In conclusion, Marburg virus infects and replicates in human primary PTC and induces downregulation of processes known to be relevant for acute kidney injury as well as a strong inflammatory response.