Completed Public Health & Healthcare Computing & AI

The OpenSafely Research Platform

In plain English

AI plain-English summary

OpenSAFELY lets approved researchers run analyses across 24 million NHS patient records without ever moving the data out of the secure system where it already sits. This matters because the NHS holds decades of detailed primary care data, but getting access to it for research has been slow and risky. Traditional approaches require copying pseudonymised patient data to external servers, which creates security vulnerabilities and delays. During the COVID-19 emergency, researchers needed answers in weeks, not years. OpenSAFELY solved that by sending the analysis code to the data, rather than the data to the analysts. The first results came back in just five weeks. If this model succeeds, it could transform how the NHS supports research. Instead of months-long data-sharing agreements and repeated security audits, researchers could run studies across millions of records quickly and safely. The platform is already open for security and scientific review, and all analytic software is reusable. This approach could become the standard for health data research in the UK, enabling faster answers to urgent public health questions without compromising patient privacy.

View original technical description
OpenSAFELY is a new secure analytics platform for electronic health records in the NHS, created to deliver urgent results during the global COVID-19 emergency. It is now successfully delivering analyses across more than 24 million patients’ full pseudonymised primary care NHS records, with more to follow shortly. All our analytic software is open for security review, scientific review, and re-use. OpenSAFELY uses a new model for enhanced security and timely access to data: we don’t transport large volumes of potentially disclosive pseudonymised patient data outside of the secure environments managed by the electronic health record software company; instead, trusted analysts can run large scale computation across live pseudonymised patient records inside the data centre of the electronic health records software company. This pragmatic and secure approach has allowed us to deliver our first analyses in just five weeks from project start.

View the original record at the funder ↗

Researchers

Ben Goldacre (EPMC Awardee)

Related Research

Grants with similar aims, by meaning.

The OpenSAFELY Collaborative
OpenSAFELY Phase Two
Urgent research and surveillance on Covid-19 using the new OpenSAFELY secure platform across 55 million patients' full linked primary care records
The OpenSafely Research Platform - Phase I: Retrospective analyses of healthcare records for COVID-19 and its effects
Open, reproducible analysis and reporting of data provenance for high-security health and administrative data

Original classification

Discretionary Award – DSH

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.