NHS Team Develops AI Tool ‘Foresight’ for Health Predictions

The new tool is trained on healthcare data and uses a deep learning approach to recognize complex patterns in both structured and unstructured data.

NHS healthcare researchers have developed an AI application tool ‘Foresight’ that can predict patients’ health outcomes.

This AI system has been developed by a team 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.

Per the researchers, Foresight could be used to support clinical decision making, monitoring in healthcare settings and clinical trials.

How Foresight Works?

Foresight runs on the Cogstack platform, which uses advanced technologies of natural language processing to extract scorable health insights from NHS electronic health record data.

Unlike the traditional methods, the new AI tool is trained on healthcare data and uses a deep learning approach to recognise complex patterns in both structured and unstructured data so as to boost its predictive powers.

A recently published study in The Lancet Digital Health, confirmed its potential. The study revealed that the software detected the forthcoming 10 disorders of patients with the most satisfactory rates over different datasets.

Foresight has also achieved a 68% accuracy at King’s College Hospital and 76% at Maudsley NHS Foundation Trust, and on the other hand, an accuracy rate of 88% in the case of the US MIMIC-III dataset.

In addition, the effectiveness of Foresight was established through a series of comprehensive assessment processes conducted by healthcare professionals.

Reportedly, the tool was comprehensive in its capability of producing clinically relevant predictions on a simulation which featured 34 mock patient timelines with the simulated scenarios.

Interestingly, more than 93% of the predictions made by Foresight were considered practical and relevant by the participating clinicians who worked both in real clinical settings and in virtual education units.

Prof 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.”

According to him, to develop effective AI tools there must be appropriate data to train models and work towards the purpose of supporting healthcare systems to support patients.

“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,” Prof Dobson added.

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.’’

The team behind Foresight is constantly improving the product and is striving to make a better product with the sole vision of achieving success.