Suchergebnisse

In the last decades, the awareness has grown among the public, as well as among health politicians, that dementia is highly prevalent in older age, that it causes much distress to patients and their families, and that it poses a large burden on public health care resources.Initially, research focused chiefly on Alzheimer's disease, the most frequent type of dementia. In recent years, there is also increasing interest in vascular dementia. The reasons for this are that vascular dementia may be more prevalent than previously recognized, that vascular causes may be involved in the clinical picture of other dementia syndromes as well, and, perhaps most importantly, that vascular causes of cognitive decline can potentially be influenced by available measures of intervention. In studies of the frequency and etiology of dementia, much emphasis has been put on differentiating demented subjects from cognitively unimpaired individuals. However, there is little evidence to support the idea of a sharp distinction between demented and non-demented persons. Cognitive impairment is a quantitative rather than a qualitative characteristic, and consequently its distribution in the population shows a continuum of severity. The fact that cognitive dysfunction is common in old age does not imply that it is intrinsic to aging; it may be normal in the sense of usual, not in the sense of natural This thesis focuses on epidemiologic studies on cognitive function and dementia. The main part is devoted to investigations of the relation between vascular risk factors and cognitive function; in these studies cognitive function was evaluated as a continuously distributed variable. In the other studies in this thesis, risk factors for dementia were investigated with dementia as a dichotomous outcome variable.

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.