- A recent study unveils AI’s capability to predict patients’ future health conditions.
- Foresight, an AI tool developed by researchers from KCL, UCL, and NHS trusts, showcases promising accuracy rates in identifying patient disorders.
- Tested on NHS and US datasets, Foresight achieves accuracy rates ranging from 68% to 88%.
- Researchers emphasize Foresight’s potential in aiding clinical decision-making and guiding clinical research efforts.
- Collaborative efforts are underway to refine Foresight 2, aiming for enhanced accuracy and broader applicability.
Main AI News:
A recent study has unveiled the potential of artificial intelligence (AI) in predicting patients’ future health conditions. Dubbed Foresight, this AI tool, akin to ChatGPT but trained on NHS electronic records, showcases promising capabilities in aiding healthcare professionals in patient monitoring and diagnostic decision-making processes.
Developed collaboratively by researchers from King’s College London (KCL), University College London (UCL), King’s College Hospital NHS Foundation Trust, and Guy’s and St Thomas’ NHS Foundation Trust, Foresight leverages extensive datasets from NHS trusts in London and a publicly available US dataset. Through rigorous training, three distinct models of Foresight were honed to anticipate ten potential patient disorders based on their medical records.
In trials conducted with NHS hospital data, Foresight demonstrated commendable accuracy rates, correctly identifying conditions 68% to 76% of the time. Impressively, when tested with US data, its accuracy soared to 88%.
Zeljko Kraljevic, a research fellow specializing in health informatics and biostatistics at KCL, emphasized the tool’s precision in predicting patient health trajectories. He noted in The Lancet Digital Health that Foresight holds significant promise in aiding clinical decision-making and steering clinical research efforts.
Echoing Kraljevic’s sentiments, Richard Dobson, a professor of medical informatics at KCL and UCL, underscored the pivotal role of AI in healthcare. As the theme lead for informatics at the National Institute for Health and Care Research (NIHR) Maudsley Biomedical Research Centre (BRC), Dobson emphasized the importance of leveraging appropriate data to train AI models effectively. He stressed the collective endeavor to bolster healthcare systems in supporting patient care through innovative AI solutions.
Looking ahead, the research team is actively seeking collaboration with additional hospitals to refine Foresight 2. This enhanced version, according to Prof Dobson, aims to be a “more accurate language model,” further amplifying AI’s potential in shaping the future of healthcare.
Conclusion:
The emergence of AI tools like Foresight signifies a significant advancement in healthcare, promising improved patient care through more accurate diagnoses and informed decision-making. This presents a lucrative opportunity for companies investing in AI-driven healthcare solutions to capitalize on the growing demand for precision medicine and predictive analytics in the market.
