Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

2026-08-17

AI Summary

This study addresses the challenges of generative modeling and epidemic event prediction using national-scale Electronic Health Records (EHRs) by constructing the first national-level EHR foundation model. Employing a 243-million-parameter Transformer decoder, the model performs autoregressive learning on data from 61 million individuals through fine-grained clinical code tokenization, enabling zero-shot inference and joint temporal representation. Although quantitative results are currently unavailable due to data access restrictions, this work releases a comprehensive methodological template and evaluation framework. Consequently, it establishes a reproducible paradigm and innovative benchmark for large-scale generative EHR modeling and healthcare event forecasting, facilitating future research in this critical domain despite present empirical limitations.

Abstract

Foresight-England (Foresight-E) is the first national-scale generative foundation model of electronic health records (EHRs), developed as a research pilot strictly for COVID-19 research. We evaluated its ability to model the direct and indirect effects of the pandemic. Trained from scratch entirely within the NHS England Secure Data Environment, Foresight-E is a 243-million-parameter transformer decoder. It was trained and evaluated on de-identified, longitudinal EHRs of approximately 61 million individuals, integrating primary/secondary care, death registrations, and COVID-19 data. Training and validation used a 90% subset (54.9 million) spanning November 2018 to December 2022; the remaining 10% (6.1 million) was held out for evaluation. Foresight-E models patient timelines autoregressively, predicting the next medical event given their prior history. At inference, it operates zero-shot, predicting any concept in its ~40,000-code vocabulary without task-specific training. Our tokenisation scheme retains the clinical granularity of ICD-10, OPCS-4, and SNOMED CT codes, jointly representing absolute and relative timing. We designed an evaluation framework for 30-day COVID-19 hospitalisation and mortality, including subgroup analyses by demographic factors and vaccination status. To assess generalisation to unseen future data and the pandemic's indirect effects, we tested the model on medical events from 2023 (beyond its training period), benchmarking against logistic regression and XGBoost. As detailed in the Project Status section, NHS England has paused access to data for the Foresight-E project, meaning quantitative results are currently unavailable. Instead, we share our strategy for tokenisation, architecture, training, inference, and evaluation as a methodological template and case study in the challenges of building population-scale EHR foundation models.

Problem

• Electronic Health Records
• Generative Foundation Model
• Medical Event Prediction
• COVID-19
• Zero-shot Learning

Innovation

• Generative Foundation Model
• Electronic Health Records
• Zero-shot Inference
• Clinical Tokenisation
• Autoregressive Modeling