OpenSAFELY

This article is about the medical records statistical platform. For the machinery communication protocol, see OpenSAFETY.

OpenSAFELY is a secure analytics platform, interfacing to NHS patient records and enabling statistical analysis of them by medical researchers. The platform was originally a collaboration between DataLab at the University of Oxford, the EHR group at London School of Hygiene & Tropical Medicine, and electronic health record software companies.^[1] The platform is now developed by the Bennett Institute for Applied Data Science, part of Oxford University's Nuffield Department of Primary Care Health Sciences.^[2]

Initially, it has been used to make an analysis of the risk factors associated with deaths from COVID-19 in hospital in the UK.^[3] This is significant because the dataset is especially large, covering about 58 million patients.^[4] In 2023, the NHS announced that it would expand the use of the OpenSAFELY platform to help drive life-saving advances for other major diseases.^[5]

The platform interfaces with a secure database of pseudonymized primary care records, and only aggregated results are viewable by researchers. This allows researchers to access a large dataset necessary for identifying potential risk factors without the risks of exposing personal patient information.^[6]

In 2025 the OpenSAFELY project was awarded a package of funding from the Wellcome Trust, this included £7 million to analyse the outcomes of talking therapies across the NHS. A further £10 million was awarded to develop data infrastructure, including investigating "new methods for connecting diverse health datasets and enhanced analytical tools for researchers".^[7]