Search

Health Data

Understand sensitive data and the challenges of using it in biomedical research

Scientific Services

Services to support research using sensitive health related data

BioMed IT Infrastructure

A secure IT environment for the responsible handling of health data as a service

Getting started

Start here to find out all you need to know before setting up your BioMedIT user account

Training & information

Find out about the training available to help you use BioMedIT

About us

Meet the people behind the BioMedIT Network, and find out what we're trying to achieve

Bringing the analysis to the data

Federated compute enables researchers to send their algorithms to a remote computational service, and run remote analysis without the need to move the original data around.

Results of remote analysis are aggregated by the federated compute service and the final results are produced while ensuring privacy protection. Federated compute benefits collaborative research use cases in which it is either not allowed, or not feasible to move data around due to ethical or legal restrictions or because of practical challenges (e.g. regarding the size of data or computational challenges).

Thanks to the secure cloud native setup of the BioMedIT nodes, they are capable of supporting various standard federated compute pipelines. So far, the network has successfully supported the following federated compute pipelines on BioMedIT network:

Personalised Health Train

The Personal Health Train (PHT) is designed to enable health care innovators and researchers to work with health data from various sources. It can give controlled access to data, while ensuring privacy protection and optimal engagement of individual patients and citizens data.

Use case: In collaboration with the university hospitals Basel (USB), the university hospitals Zurich (USZ) and sciCORE (of the University of Basel), BioMedIT constitutes the Swiss hub of the international Personal Health Train project ARGOS. As part of this project, a deep learning neural network is being trained at over 20 sites worldwide to automatically segment CTs of lung cancer.

More details: PHT Website

ELIXIR Cloud and AAI

ELIXIR Cloud & AAI develops services towards establishing a federated cloud computing network that enables the analysis of population-scale genomic and phenotypic data across different sites.

Use case: with collaboration from SIB and ELIXIR Switzerland, PoC services have been successfully deployed and tested in the BioMedIT network.

More details: ELIXIR Cloud & AAI website

Please contact BioMedIT if your project has needs for federated compute or if you would like to know more details on this topic.