Welcome to the Health Data Science Sandbox
A collaborative project with team members spanning five Danish universities
The Health Data Science Sandbox is a national project coordinated by the Center for Health Data Science at the University of Copenhagen. We’re working with a network of health data science experts to build training resources on academic supercomputers for students and researchers in Denmark. Our Sandbox contains training modules that pair topical datasets with recommended analysis tools, pipelines, and learning materials/tutorials in a portable, containerized format.
To get involved as a trainee, researcher, or educator in Denmark:
TRAINEES: join our next scheduled workshop or a supported university course
TRAINEES/RESEARCHERS: explore training modules independently on UCloud
RESEARCHERS: adapt training modules or code repositories to your research
EDUCATORS: host a training event or course in the Sandbox with our support
The Sandbox aims to be a resource for learning new analysis approaches and tools for health data science on useful, interesting, and safe-to-share datasets. All person-specific datasets in the Sandbox are non-sensitive and GDPR-safe because they are 1) sourced from public databases, 2) fully anonymous/non-sensitive from a GDPR perspective, and/or 3) synthetic. To learn more, check out Datasets where we explain our data policy in detail and our approach to synthetic data generation.
Thanks to the Novo Nordisk Foundation for funding the National Health Data Science Project! Please give credit if you use our open-source materials in any form (NNF grant number NNF20OC0063268).