A5068664919- demographic modeling and climate adaptation
- Health, Environment, Cognitive Aging
- Research Data Management Practices
- Health disparities and outcomes
- Data Quality and Management
- Artificial Intelligence in Healthcare and Education
- Machine Learning in Healthcare
- Scientific Computing and Data Management
- Data-Driven Disease Surveillance
ZB MED - Information Centre for Life Sciences
2024
As part of the BioHackathon Europe 2024, we here report on progress that both project 19 and 24 have made during event. For purpose this will present abstract projects then dive deeper what work was done BioHackathon.
Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely the availability of access large datasets. sector, often challenging due privacy concerns. A promising alternative generation fully synthetic data, i.e., generated through a randomised process that have similar statistical properties as original but do not one-to-one correspondence with records. this study, we use...
Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI); however, sharing real patient information often restricted due to privacy concerns. A promising solution this challenge synthetic generation. This technique creates entirely new datasets that mimic the statistical properties of data, while preserving confidential information. In paper, we present workflow and different services developed context Germany’s National Data...
Abstract Agriculture is confronted with several challenges such as climate change, the loss of biodiversity and stagnating productivity. The massive increasing amount data new digital technologies promise to overcome them, but they necessitate careful integration management make them usable. FAIRagro consortium part National Research Data Infrastructure (NFDI) in Germany will develop FAIR compliant infrastructure services for agrosystems science community, which be integrated existing...
Introduction: A modern approach to ensuring privacy when sharing datasets is the use of synthetic data generation methods, which often claim outperform classic anonymization techniques in trade-off between utility and privacy. Recently, it was demonstrated that various deep learning-based approaches are able generate useful synthesized datasets, based on domain-specific analyses. However, evaluating implications releasing remains a challenging problem, especially goal conform with protection...
Individual health data is crucial for scientific advancements, particularly in developing Artificial Intelligence (AI); however, sharing real patient information often restricted due to privacy concerns. A promising solution this challenge synthetic generation. This technique creates entirely new datasets that mimic the statistical properties of data, while preserving confidential information. In paper, we present workflow and different services developed context Germany's National Data...
Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely the availability of access large datasets. sector, often challenging due privacy concerns. A promising alternative generation fully synthetic data, i.e. generated through a randomised process that have similar statistical properties as original but do not one-to-one correspondence with records. this study, we use...