The PHIRI Project: Advancing Population Health Research Infrastructure

The PHIRI project aims to establish a federated research infrastructure for population health, involving 32 partners and focusing on semantic and technical interoperability challenges in health data. The project progresses through Docker containers, bespoke data models, deployment on partners' premises, and exploring automated solutions for complex algorithms and distributed statistical modeling. Moving towards the production phase, the vision includes sandboxes for synthetic data/digital twins, secure processing environments, EHDS2 liaison, and notebook-based solutions with parallel runtimes.

• Population Health Research
• Data Interoperability
• Federated Infrastructure
• Docker Containers
• Automated Analysis

brynle Follow

Uploaded on Nov 28, 2024 | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

Presentation Transcript

1. The PHIRI project: advances towards an infrastructure for population health research Juan Gonz lez-Garc a, IACS, ES

2. Background Health Data: Highly sensitive data space Difficult to gather data Poor semantic interoperability Poorer technical interoperability

3. PHIRI project Objective: set the grounds to build a federated research infrastructure for population health 32 partners + 6 LTPs WP6 use cases (4) WP7 infrastructure development

4. PHIRI solution v1 Docker containers Bespoke common data models (CMD) per use case Deployment on partners premises Client server with high human intervention Local analyses per node Central meta-analysis Available @ ZENODO https://zenodo.org/record/6936063

5. PHIRI solution v2 Keep container solutions Provide multi-container recipes Move to single CDM (OMOP) ? Evaluate deployment @ EGI-ACE premises Reduce human intervention Automated (partial) results exchange Complex algorithms Distributed statistical modelling Federated learning

6. Vision for production phase of the RI Sandboxes (Synthetic data/Digital Twins) Development env Secure Processing Environments (Real world data) Production env EHDS2 (HealthData@EU) liaison Notebook based solutions With parallel runtimes