A pilot study is training an artificial intelligence model on a de-identified set of 57 million people in England to save lives.
A pilot study is being run by researchers at the Institute of Psychiatry, Psychology & Neuroscience (IoPPN) at King’s College London and University College London (UCL) to train an artificial intelligence model that will identify opportunities where early interventions might significantly improve or save lives.
The pilot operates entirely within the NHS England Secure Data Environment (SDE), a secure data and research analysis platform, and the model is being trained on a set of NHS data for 57 million people in England from November 2018 to the end of 2023 that has been de-identified.
The data was originally made available for COVID-19 research.
By including data covering England’s entire population, the model can be used to make predictions about health outcomes across all demographics and for rare conditions.
An earlier version of the model, called Foresight, was previously trialled within two NHS Foundation Trusts (King’s College Hospital and South London and Maudsley) as part of a collaboration between King’s, UCL, the National Institute for Health and Care Research (NIHR) Maudsley Biomedical Research Centre (BRC) and NIHR UCLH BRC.
Window of opportunity
The researchers believe the model’s predictive power could pinpoint high-risk patient groups, and open up a window of opportunity to intervene to improve and save lives. Due to the diversity and completeness of the training data, the model could also help to highlight and address healthcare inequalities. And the ability to analyse healthcare risks and outcomes on a population level could offer critical support to the NHS when it comes to planning.
“AI models are only as good as the data on which they’re trained. So if we want a model that can benefit all patients, with all conditions, then the AI needs to have seen that during training,” said Chris Tomlinson, co-lead researcher from UCL, who emphasised that national-scale data allows the model to represent particularly minority groups and rare diseases which, he said, are often excluded from research.
The government recently announced the development of a Health Data Research Service, designed to support secure access to data for health researchers. The service is designed to ensure that projects like Foresight, which securely and safely access data to drive innovation and improve patient lives, will be much easier to support.
Foresight is a collaboration between NHS England, King’s College London, UCL NIHR Maudsley BRC, NIHR UCLH BRC, King’s College Hospital NHS Foundation Trust, South London and Maudsley NHS Foundation Trust, British Heart Foundation Data Science Centre’s CVD-COVID-UK/COVID-IMPACT Consortium, AWS, Databricks and CogStack. It is funded by NHS AI Lab, UK Research and Innovation, Medical Research Council, NIHR and Health Data Research UK.
