In this session, we showcase a collaborative project with NortHFutures, Teesside University, Newcastle University, and Hull and East Riding Frailty Hospital at Home Virtual Ward that solved this data deadlock. We developed an open-source, OMOP-based synthetic data generator specifically for virtual hospital scenarios. This tool creates believable, realistic patient populations (complete with realistic vital signs, symptom surveys and social deprivation markers) without utilising a real patient record.
We will demonstrate how this approach allows multidisciplinary teams to test intervention thresholds and explore healthcare inequalities in a safe-to-fail environment. Attendees will learn how synthetic data, mapped to the international OMOP standard, can accelerate the development of AI-driven decision support and ensure that new care models are safe, inclusive and grounded in reality from day one.
- Accelerating innovation: How to use synthetic data to design and test clinical pipelines in parallel with information governance processes, reducing project lead times.
- The Power of OMOP: Why using the Common Data Model (CDM) ensures AI models and dashboards are "plug-and-play" for live NHS environments.
- Modelling inequality: Practical methods for integrating deprivation and geography data to see how care outcomes vary across different communities.
- Open-source collaboration: How to access and implement the virtual ward generator for your own Trust or integrated care system.
- Scaling impact: How identifying complex cases with high accuracy (<2.2% false positives) allows frontline staff to devote more time to direct patient treatment.
- Ed Hiley, Technology Director - Healthcare, Hippo
