A federated analytics platform for clinical research networks that need to collaborate on sensitive health data without centralizing patient-level records. More information is available on the MIP Website.
- About MIP
- 9.1 Release
- What MIP Includes
- Deployment
- Federated Analysis Algorithms
- Data Management
- Architecture
- Onboarding
The Medical Informatics Platform enables privacy-preserving analysis across distributed clinical datasets. Hospitals and data providers keep patient-level data within their local governance boundaries, while researchers can run federated statistical and machine-learning analyses across participating sites.
This repository collects the technical, deployment, data-management, and architecture documentation needed to understand, deploy, and operate MIP.
MIP 9.1 expands the range of analyses that can be performed across distributed clinical datasets without moving patient-level data. The release adds support for advanced statistical workflows such as survival analysis, association testing, histogram exploration, outlier reporting, and mixed-effects modeling, while refreshing the documentation for the core analysis portfolio.
The analysis experience has been refined to make experiment setup and result review clearer. Users get better guidance when selecting variables, clearer feedback when an analysis cannot run with the selected inputs, and improved result views with more consistent tables, charts, labels, and export actions.
MIP 9.1 introduces more data preparation options directly into the analysis workflow. Missing-value handling, outlier handling, and longitudinal transformations can be configured before running an analysis, reducing the need for manual preparation outside the platform.
The platform has been updated with refreshed deployment defaults and reviewed documentation for deployment, data management, architecture, and onboarding, making MIP easier to operate and evolve across research infrastructures.
MIP combines a web interface, backend services, federated analysis engine, deployment tooling, and supporting data-management tools. The main MIP building blocks are listed with the repositories that host them.
MIP supports both local development deployments and Kubernetes-based deployments for production-like or federated installations.
The algorithm documentation describes the available federated analyses and links to the underlying Exaflow analytic engine documentation.
The data-management documentation explains how datasets and metadata are prepared for use in MIP.
A detailed user guide for the Data Quality Control tool can be found here:
Data Catalog is a component of MIP for EBRAINS. It enables management, visualization, and access to data models and medical conditions.
- High-level view of the architecture, the main building blocks and data flows.
- Onboarding to the Medical Informatics Platform MIP on EBRAINS Collaboratory
This project/research received funding from the European Union’s Horizon 2020 Framework Programme for Research and Innovation under the Framework Partnership Agreement No. 650003 (HBP FPA).