Researchers in Oxford have developed a new, easy-to-use technique for hospitals to contribute to the development of artificial intelligence (AI) models, without patient data leaving the hospital’s premises.
Due to the need to safeguard patient privacy, hospitals are often limited in the data they can share to support the development of AI algorithms, as once data has been shared it can be difficult to guarantee it remains confidential.
Federated learning was developed in 2017 as a way to train AI algorithms without moving data, and researchers around the world have been working with major technology companies to study how it can be applied in healthcare systems, including in the NHS. However, there has been limited uptake of federated learning in hospitals, in part because its deployment often needs specialist expertise at each hospital taking part in the AI development.
In a paper published in The Lancet Digital Health, Oxford researchers have developed and piloted a new technique – called full-stack federated learning – where the software is pre-bundled with inexpensive microcomputing hardware, to make a ‘plug-and-play’ system that is easy for hospitals to deploy. Hospitals taking part in the AI development are sent ‘ready to use’ devices that can be quickly set up, without needing an expert in federated learning onsite.
The researchers hope that the new scalable approach, developed with support from the National Institute for Health and Care Research (NIHR) Oxford Biomedical Research Centre, could help address some of the privacy concerns around training AI models using patient data, and lead to models that are more representative and perform more fairly.
In the paper, the team demonstrate the new technique by deploying Raspberry Pi 4 micro-computers, at a cost of £45-85 per hospital, to train and validate a screening test for COVID-19 in emergency departments, without the patient data ever leaving the hospitals’ premises. The four hospital groups taking part in the pilot were University Hospitals Birmingham NHS Foundation Trust, Bedfordshire Hospitals NHS Foundation Trust, Portsmouth Hospitals University NHS Trust and Oxford University Hospitals (OUH) NHS Foundation Trust.
The micro-computers were preloaded with the software needed to perform federated learning and sent to the NHS trusts. Staff at the hospitals could set the devices up quickly and took part in federated training and calibration to predict COVID-19 status using clinical data from pre-pandemic admissions and COVID-19-positive cases from the first wave. This allowed the researchers to develop a cross-site (global) AI model, which was then evaluated for admissions to three of the NHS Trusts during the second wave.
The results showed that federated techniques improved the performance of the AI model by 27.6%, when compared to the performance of models trained using just an individual hospital’s data, and that the federated model generalised well across sites, making it safe and effective to use.
The Oxford team previously developed an AI test to rapidly screen patients arriving in emergency departments for COVID-19 using clinical information routinely available within the first hour of coming to hospital, but in previous work had centralised the data at the University of Oxford.
The study was led by Dr Andrew Soltan, NIHR Academic Clinical Fellow at the University of Oxford, and Oncology Specialty Registrar and Fellow in Clinical Artificial Intelligence at OUH. He said: “Building AI models that are fair and inclusive is most achievable when models can be trained with diverse data. Sometimes that might mean training models using data from different parts of the UK, and sometimes also working with data from abroad.
“Rather than asking hospitals to shoulder the technical burden of taking part in the federated learning, our new approach meant that we - as researchers - did as much of the set-up as possible ourselves before the devices reached the hospitals. By making it easy to train models without moving data, we hope our new full-stack federated learning approach can lead to better and fairer models, which can be developed more quickly, while respecting patient privacy and data sovereignty laws. Together, this might pave the way for the kinds of AI interventions that will lead to improvements for patients in the NHS and those abroad.”
Professor David Eyre, Professor of Infectious Diseases at the University of Oxford’s Big Data Institute and an OUH consultant, is a co-author on the study. He added: “This is a really exciting development that could see hospitals from across the NHS working together to build AI tools to improve patient care, without any patient data ever having to leave each hospital. This tool could have really made a difference during COVID, and we are aiming to have tools like it in use in the NHS in the near future.”
Professor David Clifton, Chair of Clinical Machine Learning at Oxford and NIHR Research Professor, described the project as “an exciting demonstration of getting safe, reliable AI models into the NHS, showing the potential of contemporary AI for contributing to patient care. Federated learning allows us to ‘have our cake and eat it’, in that we can develop useful tools within the hospital’s secure systems, while linking models – and not data – across hospital sites in a manner that demonstrably adheres to best-practice governance for patient data.”
The National Institute for Health and Care Research (NIHR) Oxford Biomedical Research Centre (BRC) is based at the Oxford University Hospitals NHS Foundation Trust and run in partnership with the University of Oxford.
The mission of the NIHR is to improve the health and wealth of the nation through research and is funded by the Department of Health and Social Care. Its work in low- and middle-income countries is principally funded through UK Aid from the UK government.