FORESIGHT: A novel GPT-based pipeline trained on NHS data

February 7, 2023

Zeljko Kraljevic outlines how these foundation models for medicine can provide the potential for a diverse integration of medical data that includes electronic health records, images, lab values, biologic layers such as the genome and gut microbiome...

Over the past four years, the AI world has surged ahead with large language models (LLMs), also known as “foundation models” which can be adapted to achieve many linguistic tasks. You’ve probably seen a plethora of articles in the media recently about some of these models (ChatGPT, Dalle-2), that can write coherent essays, write code, but also generate art and films, and many other capabilities. 

With the NHS at breaking point, a critical question is whether these AI approaches could be used to improve care. Hospital records hold detailed information about each patient's health status and general clinical history, a large portion of which is stored within the unstructured text. Temporal modelling of this medical history, which considers the sequence of events, could be used to forecast and simulate future events, estimate risk, suggest alternative diagnoses or forecast complications. 

I have developed Foresight as part of the CogStack platform, a novel GPT-based pipeline that is trained on NHS data to forecast future medical events such as disorders, medications, symptoms and interventions.

On tests in two large King’s Health Partner hospitals (King’s College Hospital, South London and Maudsley) and the US MIMIC-III dataset Foresight performed well when set challenges by clinicians. The model is being used for many uses including real-world risk estimation, virtual clinical trials and clinical research to study the progression of diseases, simulate interventions and counterfactuals, and for educational purposes.


 Medical AIs are advancing - when will they be in a clinic near you?  Read the  New Scientist article

Share

May 18, 2026
We are delighted to welcome Luis Garcia-Gancedo , Executive Director and Head of Digital Medicine at GSK , to speak at our symposium and partner showcase next month. Luis will deliver his talk “Digital Medicine in Clinical Development: Innovation at the Industry-Academia Interface " Abstract: Digital Medicine is transforming clinical trials, with wearable devices, digital endpoints, decentralised trial technologies and AI-driven insights already integrated into many clinical development programmes. This presentation will provide an overview of the current landscape and will discuss the opportunity for industry-academia collaborations to overcome existing barriers (including evidence generation to support validation and regulatory acceptance) to propel the field forward for the benefit of patients. Date and Time: Thursday 11 June 2026, 10:00 hrs (BST) Location: The Science Gallery London, Guy's Campus Tickets are free, please register as spaces are limited : https://buytickets.at/kingsepsrcdrivehealthcentrefordoctoraltrainingindatadrivenhealth/2143742 Biography Luis Garcia-Gancedo is an Executive Director and Head of Digital Medicine at GSK. In this role, he streamlines the consideration of digital health technologies in GSK’s respiratory, immunology and inflammation clinical trials, transitioning from an opportunistic to a strategic approach for developing and deploying novel digital solutions that address key clinical development challenges. Prior to his current role, he was with AstraZeneca, GSK, and the University of Cambridge. Luis holds a BSc/MSc in Physics, a PhD in Engineering and an Executive MBA.
April 28, 2026
Bridging Academia and Industry: Turning Health Data into Health Solutions Please join us for the EPSRC DRIVE‑Health CDT Summer Symposium & Partner Showcase 2026 , a two‑day event dedicated to bridging academia and industry and accelerating the journey from health data research to real‑world solutions. This year’s theme, “Bridging Academia and Industry: Turning Health Data into Health Solutions", brings together our vibrant community of students, King’s academics, industry partners, clinicians and policymakers to explore how collaboration can unlock new insights, innovation and impact across health and care. Event details 📅 11 & 12 June 2026 📍 Science Gallery London, Guy’s Campus, King’s College London, Great Maze Pond, London SE1 9GU Timings: ⏰ 10:00–16:00 each day ☕ Refreshments available from 09:30 👉 Please be seated by 09:50 for a prompt 10:00 start Please secure your place here: Register Now Programme highlights KEYNOTE ✨ Dr Luis Garcia‑Gancedo , Executive Director & Head of Digital Medicine – Respiratory, Immunology & Inflammation, GSK INTERACTIVE DEBATE ✨ Student‑led interactive debate exploring AI within the context of the event theme: “Bridging Academia and Industry: Turning Health Data into Health Solutions.” PANEL DISCUSSION & POSTER JUDGING ✨ “What does industry actually need from health data PhDs - and how can industry partner with academia for maximum impact?” Panelists confirmed so far: Dr Laura Acqualagna , Director of AI/ML Engineering, GSK R&D Dr Chris Callaghan , Consultant Transplant Surgeon, Guy’s Hospital Dr Nina Sesto , CEO & Co‑Founder, MEGI Health Dr Srinivasan Vairavan , Director of Data Science & Digital Health, JNJ Innovative Medicine R&D, and Visiting Adjunct Faculty, King’s College London Dr Nicolas Huber , Director, King’s Innovation Catalyst PLUS ✨ Student lightning talks (across both days) ✨ 3‑minute Student Spotlight Slides (across both days) ✨ Poster showcase & networking session (Friday) ✨ Prizes for outstanding contributions (Friday) Please secure your place here: Register Now If you are no longer able to attend the event, please email drive-health-cdt@kcl.ac.uk so that we can reallocate to our waiting list.