Artificial intelligence is transforming healthcare research, but how do we know an algorithm developed in one setting will perform reliably in another?

An upcoming webinar on Monday 19th October, 11:00-11:45 am, will showcase a pioneering research project led by Imperial College London, which is using de-identified patient data within the Eastern England Secure Data Environment (SDE) to externally validate a machine learning model designed to predict hospital-acquired pressure ulcers.

External validation is a critical step in AI development. By testing the algorithm on data from a different population and healthcare setting to the one in which it was originally developed, researchers can assess whether it can accurately identify patients most at risk and determine its potential for wider clinical adoption.

The session will provide a behind-the-scenes look at the research process and explore both the opportunities and challenges involved in translating AI from research into meaningful clinical impact. Attendees will also hear how secure data environments can help streamline access to data for research while maintaining robust patient privacy protections.

The webinar will be particularly relevant for researchers, innovators and healthcare professionals interested in accessing de-identified NHS data for research purposes. Participants will gain practical insights into current data availability, routes to data access and the experience of conducting analysis within the Eastern England SDE.

Simon Erridge, a researcher currently undertaking the pressure ulcer validation study within the SDE, will share key learnings from the project and discuss the role of real-world data in evaluating machine learning models.

To learn more about this project: External validation of a machine learning algorithm for predicting hospital-acquired pressure ulcers using de-identified patient data from the East of England - Eastern England SDE

What is the SDE?

The Eastern England SDE is addressing one of the biggest barriers to research: secure and timely access to high-quality clinical data. Researchers can now apply once-through a single governance route-to access data from multiple NHS sites. Unlike a traditional data lake, the Eastern England SDE ingests data on demand, providing secure, relevant and up-to-date access to datasets including secondary prescribing data, lab results, diagnostics and longitudinal health records that are hard to access elsewhere. Rapid cohort discovery reduces feasibility timelines from months to a matter of hours and standardised, longitudinal data from multiple NHS sites reduces cost and complexity in multi-site studies. The platform supports bringing your own data, testing AI models, assessing device feasibility and collaborating - all within one secure environment.

Register to attend the webinar here.

For any queries about this event, please email This email address is being protected from spambots. You need JavaScript enabled to view it.