A team of NHS healthcare researchers have developed an AI tool to predict the health trajectory of patients.
They have indicated that the tool, named Foresight, could be used to support clinical decision making, monitoring in healthcare settings and clinical trials.
The team consists of researchers from two London NHS foundation trusts – King’s College Hospital and Guy’s and St Thomas’ – and King’s College and University College London.
They have developed Foresight on the Cogstack information retrieval and extraction platform, which uses national language processing to harness NHS electronic health record data. The new tool is trained on healthcare data and uses a deep learning approach to recognise complex patterns in both structure and unstructured data.
A study of the tool’s potential, published in The Lancet Digital Health, found that Foresight correctly identified the next 10 possible disorders in a patient timeline 68% of the time at King’s College Hospital and 76% at Maudsley NHS Foundation Trust, and 88% of the time in the US MIMIC-III dataset.
Simulation assessment
Another assessment involved five clinicians developing 34 mock patient timelines with simulated scenarios. Foresight produced predictions of which 93% were judged to be relevant, meaning they made sense from a clinical perspective.
A report by the NIHR Maudsley Biomedical Research Centre said that Foresight can be used for real world risk forecasting, emulating trials and clinical research to study the progression of disorders and simulate interventions.
Professor Richard Dobson, professor of medical informatics at King’s College London and senior author of the study, said: “Foresight opens the door for many applications such as digital health twins, synthetic dataset generation, real world risk forecasting, longitudinal research, emulation of trials, medical education and more.
“It is an exciting time for AI in healthcare and to develop effective tools we must ensure that we use appropriate data to train our models and work towards a shared purpose of supporting healthcare systems to support patients.”
He added: “Foresight will improve with more real world data, and we are now looking for more hospitals to be involved in developing Foresight 2, a more accurate language model.”
Sources of funding
The study received funding from the NHS AI Lab, the National Institute for Health and Care Research and Health Data Research UK (HDRUK).
Professor Andrew Morris, director of HDRUK, commented: This work demonstrates the potential that using electronic health records and the latest advancements in AI could deliver for improving clinical decision making.
“But this is all dependent on the quality and representativeness of data. Sustained investment in the UK's data infrastructure is needed to enable this in safe and secure ways to maintain privacy and anonymity of people's health data.”
