Refine
Year of publication
- 2022 (2) (remove)
Document Type
- Article (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Comparative analysis (1)
- Deep neural network (1)
- Gradient boosting (1)
- Multi-syndrome classification (1)
- Neurodegenerative syndromes (1)
- Random forest (1)
- Support vector machine (1)
- beta2-adrenoceptor (1)
- cartilage (1)
- leptin (1)
Institute
- Medizin (2)
Purpose: Recent studies demonstrated a contribution of adrenoceptors (ARs) to osteoarthritis (OA) pathogenesis. Several AR subtypes are expressed in joint tissues and the β2-AR subtype seems to play a major role during OA progression. However, the importance of β2-AR has not yet been investigated in knee OA. Therefore, we examined the development of knee OA in β2-AR-deficient (Adrb2-/-) mice after surgical OA induction.
Methods: OA was induced by destabilization of the medial meniscus (DMM) in male wildtype (WT) and Adrb2-/- mice. Cartilage degeneration and synovial inflammation were evaluated by histological scoring. Subchondral bone remodeling was analyzed using micro-CT. Osteoblast (alkaline phosphatase - ALP) and osteoclast (cathepsin K - CatK) activity were analyzed by immunostainings. To evaluate β2-AR deficiency-associated effects, body weight, sympathetic tone (splenic norepinephrine (NE) via HPLC) and serum leptin levels (ELISA) were determined. Expression of the second major AR, the α2-AR, was analyzed in joint tissues by immunostaining.
Results: WT and Adrb2-/- DMM mice developed comparable changes in cartilage degeneration and synovial inflammation. Adrb2-/- DMM mice displayed elevated calcified cartilage and subchondral bone plate thickness as well as increased epiphyseal BV/TV compared to WTs, while there were no significant differences in Sham animals. In the subchondral bone of Adrb2-/- mice, osteoblasts activity increased and osteoclast activity deceased. Adrb2-/- mice had significantly higher body weight and fat mass compared to WT mice. Serum leptin levels increased in Adrb2-/- DMM compared to WT DMM without any difference between the respective Shams. There was no difference in the development of meniscal ossicles and osteophytes or in the subarticular trabecular microstructure between Adrb2-/- and WT DMM as well as Adrb2-/- and WT Sham mice. Number of α2-AR-positive cells was lower in Adrb2-/- than in WT mice in all analyzed tissues and decreased in both Adrb2-/- and WT over time.
Conclusion: We propose that the increased bone mass in Adrb2-/- DMM mice was not only due to β2-AR deficiency but to a synergistic effect of OA and elevated leptin concentrations. Taken together, β2-AR plays a major role in OA-related subchondral bone remodeling and is thus an attractive target for the exploration of novel therapeutic avenues.
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.