NHS healthcare researchers have developed an AI application named Foresight through collective effort. This system would be based on AI, so it should be able to predict patients’ health outcomes more effectively than current methodologies. This innovative system has been developed by a team of researchers from the London NHS Foundation trust organization, including Kings College Hospital and Guy’s and St Thomas’, in conjunction with academic institutions such as King’s College London and University College London. Foresight thus remains a step forward in assisted clinical decision-making and health monitoring.
Harnessing AI for clinical decision making
Foresight runs on the Cogstack platform, which uses advanced technologies of natural language processing to extract scoreable health insights from NHS electronic health record data. Unlike the traditional methods, Foresight employs deep learning techniques for the recognition of complicated flows within structured as well as unstructured data so as to boost its predictive powers.
Foresight, a recently published study in The Lancet Digital Health, confirmed its potential. The effective software detected the forthcoming 10 disorders of patients with the most satisfactory rates over different datasets. On the one hand, Foresight achieved a 68% accuracy at King’s College Hospital and 76% at Maudsley NHS Foundation Trust, and on the other hand, an impressive 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. The tool was comprehensive in its capability of producing clinically relevance predictions on a simulation which featured 34 mock patient timelines with the simulate 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.
Real-world applications and future prospects
According to a National Institute of Health Research Maudsley Biomedical Research Centre report, Foresight has much potential in modern health care, for instance, real-world risk forecasting and clinical research emulation. Apart from its role in clinical decision-making, this tool has implications extending along the research spectrum as well as medical education and emulation of clinical trials. Professor Richard Dobson, the main author of the research, highlighted that Foresight has a leading role in the development of AI healthcare systems. He also stressed that real-world data is key to enhancing the accuracy and effectiveness of Foresight-based systems
The funding for the Foresight design and implementation was met by different organizations which included the NHS AI Lab, National Institute for Health and Care Research, and HDRUK. This investment makes it possible to protect individual privacy and encourage the widespread use of technological solutions in the healthcare sector, such as Foresight, in which predictive powers can be claimed.
The team behind Foresight is constantly improving the product and is striving to make a better product with the sole vision of achieving success. Foresight 2, which is conceived to be a more powerful successor of Foresight 1, will harness data from many other hospitals to enhance its prediction. It will further help to expand the applicability of this tool beyond healthcare contexts which are unique.
This article originally appeared in The National Health Service.
