NHS Deploys AI Model ‘Foresight’ to Predict Disease Risk Using Data from 57 Mn People

Unlike generative AI tools that complete text prompts, Foresight is designed to forecast potential health complications and disease trajectories.

A new artificial intelligence (AI) tool trained on anonymized health data from 57 million people in England is set to transform the UK’s approach to disease prevention and personalized medicine. 

The AI model, known as Foresight, is being developed through a world-first study led by researchers at University College London (UCL) and King’s College London (KCL), with support from NHS England.

Using cutting-edge machine learning techniques similar to those behind ChatGPT, Foresight aims to predict a patient’s future health conditions based on their medical history, enabling earlier interventions and more efficient healthcare delivery.

AI That Predicts Future Health Risks

Unlike generative AI tools that complete text prompts, Foresight is designed to forecast potential health complications and disease trajectories. 

During its pilot phase, the model is being trained on eight routinely collected datasets from across England, including hospital admissions, A&E visits, and Covid-19 vaccination records.

All datasets have been de-identified, ensuring patient privacy, and are accessed through NHS England’s Secure Data Environment, which guarantees stringent data protection protocols.

According to Dr Chris Tomlinson of UCL, one of the project leads, Foresight represents a major leap toward proactive healthcare. 

“Foresight is a really exciting step towards being able to predict disease and complications before they happen, giving us a window to intervene and enabling a shift towards more preventative healthcare at scale,” he said.

Real-World Applications: Predicting Hospitalizations

One key use case involves identifying individuals at risk of unscheduled hospitalisations, a significant event often indicating a deterioration in health. 

By understanding the underlying causes of such deterioration, clinicians could intervene earlier with tailored measures, such as medication adjustments, to prevent complications like strokes or heart attacks.

“We can use Foresight to look across the whole population and predict the risk of unscheduled hospitalisation,” Dr Tomlinson explained. 

“Then we can understand the drivers for that deterioration and potentially suggest personalized opportunities for intervention.”

Initially Focused on COVID-19 Outcomes

Currently, the model’s application is limited to COVID-19-related research. However, it can help predict virus outcomes and potentially inform responses to future pandemics. 

However, researchers are already evaluating Foresight’s ability to generalize to other healthcare outcomes, including predicting the risk of hospitalization, mortality, and the onset of over 1,000 different health conditions.

Future plans involve incorporating richer, unstructured data sources, such as physicians’ notes, lab test results, and scanned images, to further refine the model’s predictive capabilities.

A National Healthcare Asset in the Making

Professor Richard Dobson, deputy director of the NIHR Maudsley Biomedical Research Centre and co-lead researcher from KCL and UCL, emphasized that the pilot builds on previous work that tested Foresight using data from two NHS trusts. 

“To be able to use it in a national setting is very exciting, as it will potentially demonstrate more powerful predictions that can inform services nationally and locally,” he said.

The model’s rollout at scale reflects the UK government’s broader ambitions to harness AI for public benefit. 

Dr Vin Diwakar, NHS England’s national director of transformation, stated: “The NHS Secure Data Environment has been fundamental to this pioneering research, shaping a future where earlier treatments and interventions are targeted to those who will benefit, preventing future ill health.”

Govt Backs AI for Healthcare & Economic Growth

The project has received strong backing from policymakers. Science and Technology Secretary Peter Kyle called the Foresight pilot “ambitious” and emblematic of the government’s commitment to modernizing the NHS and driving economic growth through innovation.

“This research shows how AI, paired with the NHS’s wealth of secure and anonymized data, is set to unlock a healthcare revolution,” he said. 

“This technology is transforming what’s possible in tackling a host of debilitating diseases—from diagnosis, to treatment, to prevention.”

He added that stringent data privacy measures are central to the program: “An unrelenting focus on privacy and security means people can rest assured that their data is in safe hands.”

Stay tuned for more such updates on Digital Health News.