Refine
Document Type
- Article (2)
- Working Paper (1)
Language
- English (3)
Has Fulltext
- yes (3)
Is part of the Bibliography
- no (3)
Keywords
- Comparative analysis (1)
- Deep neural network (1)
- Gradient boosting (1)
- Mongolia (1)
- Multi-syndrome classification (1)
- Neurodegenerative syndromes (1)
- Random forest (1)
- Support vector machine (1)
- aging (1)
- cognitive decline (1)
- cognitive training (1)
- mild cognitive impairment (1)
- neuropsychology (1)
- nomadic lifestyles (1)
- plasticity (1)
- rangeland ecosystems (1)
- rehabilitation (1)
- rural-urban migration (1)
- steppe ecosystem (1)
- wildlife mobility (1)
- working memory training (1)
Institute
- Medizin (1)
- Psychologie (1)
The Eastern Steppe of Mongolia is one of the world's largest mostly intact grassland ecosystems and is characterised by a close coupling of societal and natural processes. In this ecosystem, mobility is one of the key characteristics of wildlife and human societies alike. The current economic development of Mongolia is accompanied by extensive societal transformation and changes in nomadic lifestyles, which potentially affects the unique steppe ecosystem and its biodiversity. The changing lifestyles are mainly characterised by rural-urban migration, resulting in reduced mobility of herders and their livestock, and presumably affecting wildlife. The question is how mobility can be fostered under these transformation processes. Time is pressing as a new generation is born which is growing up in urban environments and with new skill sets but a potential loss of the tight connection to nature and the nomadic lifestyle.
Background: Scientifically evaluated cognitive intervention programs are essential to meet the demands of our increasingly aging society. Currently, one of the “hottest” topics in the field is the improvement of working memory function and its potential impact on overall cognition. The present study evaluated the efficacy of WOME (WOrking MEmory), a theory-based working memory training program, in a double-blind, placebo-controlled, and randomized controlled trial (www.drks.de, DRKS00013162).
Methods: N = 60 healthy older adults were allocated to (1) the WOME intervention, (2) an active low-level intervention, or (3) a passive control group. Overall, the intervention groups practiced twelve sessions of 45 min within 4 weeks of their respective training. Transfer effects were measured via an extensive battery of neuropsychological tests and questionnaires both pre-/post-training and at a 3-month follow-up.
Results: WOME led to a significant improvement in working memory function, demonstrated on a non-trained near transfer task and on two different composite scores with moderate to large effect sizes. In addition, we found some indication of relevant impact on everyday life. The effects were short-term rather than stable, being substantially diminished at follow-up with only little evidence suggesting long-term maintenance. No transfer effects on other cognitive functions were observed.
Conclusion: WOME is an appropriate and efficient intervention specifically targeting the working memory system in healthy older adults.
Trial Registration: German Clinical Trials Register (DRKS), Identifier: DRKS00013162.
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.