PyData Leeds: NHS Test Data Hackathon
We are thrilled to announce the first in-person meetup for the NHS data community! This landmark event brings together NHS data professionals to collaboratively tackle one of our most pressing challenges: generating high-quality test data.
The challenge of high-quality test data in the NHS:
Creating realistic and compliant test data is a significant hurdle within the NHS. High-quality test data is essential for developing, testing, and deploying healthcare solutions without compromising patient confidentiality. The complexity of healthcare data, coupled with strict privacy regulations, makes this an ongoing challenge that impacts efficiency and innovation across the NHS.
What we’ll tackle:
- Understanding the challenges: Delve into the difficulties of generating high-quality test data within the NHS framework.
- Test data generation: Develop methods to create synthetic inpatient data and Commissioning Data Sets (CDS) that accurately reflect real-world scenarios.
- Tool exploration: Utilise tools like the NHS AI Lab’s synthetic data generator and Polyfactory to prototype solutions.
- Collaborative prototyping: Set up Google Colab environments, load analogs of typical NHS data schemas, and innovate on data generation techniques.
- Defining success: Establish criteria for effective test data, focusing on data similarity, distribution accuracy, and maintaining relational integrity.
Agenda:
- 3:00 PM – Welcome and introduction
- Opening remarks highlighting the importance of high-quality test data and its impact on NHS projects.
- 3:15 PM – Overview of objectives and tools
- 3:30 PM – Team formation and hackathon kick-off
- 6:30 PM – Pizza break and networking
- 7:00 PM – Team presentations of solutions
- 7:45 PM – Closing remarks
- Discussion on the significance of this first in-person meetup and future community events.
- 8:00 PM – Event concludes
Additional highlights:
- Community milestone: Celebrate the inaugural gathering of the NHS data community, fostering connections and collaboration.
- Collaborative effort: Proudly sponsored by PyData and Hippo, enhancing the resources and experience for attendees.
- Presentations: Share and learn from team solutions, gaining insights into various approaches and methodologies.
- Recording: While live streaming isn’t available, we’ll film introductions and presentations to create a highlight reel for the community.
Who should attend:
- NHS data professionals eager to address test data challenges.
- Individuals passionate about data generation, synthetic data, and improving NHS data practices.
What to bring:
- A laptop with access to Google Colab.
- Enthusiasm, ideas, and a collaborative spirit.
