A new artificial intelligence programme is being developed which could transform the and enable it to predict who is about to fall ill.

Health data from the whole population of England is being used to train AI as part of a world-first study which the Government says could spark a “healthcare revolution”. It will use anonymised data including on hospital admissions, A&E attendances and Covid-19 vaccination rates to eventually predict disease and complications before they happen. Patients could be contacted by the NHS and offered treatment or support to prevent them deteriorating. The programme will eventually predict patients' risk of hospitalisation or death in the next year, as well as the onset of over 1,000 different conditions.

The Government has granted access to eight routinely collected datasets covering 57 million people to researchers at University College London and King's College London. Science and Secretary Peter Kyle said: "This ambitious research shows how AI, paired with the NHS's wealth of secure and anonymised data, is set to unlock a healthcare revolution. This technology is transforming what's possible in tackling a host of debilitating diseases, from diagnosis, to treatment, to prevention.”

READ MORE:

READ MORE:

The model, known as Foresight, will use the huge data collected by the NHS to work out which combination of health circumstances often result in someone falling ill or deteriorating. One example is when frail people are at risk of a fall in the home.

Dr Omid Rohanian, senior research associate at Oxford University, who is not involved in the research, said Foresight “could transform how we approach healthcare and make a real difference in people’s lives”. He said: “The Foresight AI initiative is a promising step forward in using AI to enhance healthcare. By training on de-identified NHS data at such a large scale, it has the potential to identify health issues early and strengthen preventative care across England and beyond.”

Once the AI programme is trained on NHS patient data then in future Foresight could be used to enable the health service to contact patients whom the algorithm suggests are at high risk of a particular health harm. However, the focus of it is likely to be people who already have chronic health conditions and regular contacts with the NHS.

Dr Wahbi El-Bouri, senior lecturer at the University of Liverpool, who is not involved in the research, said: “Prevention of disease is a key goal of the NHS to reduce pressure on the health service. While such a project may go some way towards this goal by predicting what may happen next for a patient, for example if they are at higher risk of a heart attack, it does not tackle real prevention of illness.

“NHS data is the wrong type of data to tackle prevention as when someone has visited the NHS it is because something is already wrong. As a result, we miss out on learning from healthy individuals whose data is rarely collected.”

A previous trial trained the Foresight programme using data from two NHS trusts and now it will be expanded nationwide. Dr Chris Tomlinson, of UCL, said: "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.

"And to give a practical example of what that actually looks like, we could use Foresight to look across the whole population and predict the risk of, for example, unscheduled hospitalisation. This is a really significant event that often heralds deterioration in the patient's health but can occur from a variety of different causes, and also has a major resource implication on the health service.

"We can then use Foresight to understand the drivers for that deterioration, and potentially suggest personalising opportunities for intervention so that might include, for example, optimising medications to improve control and reduce the risk of, say, stroke."

The pilot study will operate within NHS England's Secure Data Environment, which will provide access to de-personalised records with patient data remaining under NHS control. The project will spark fresh fears about the security of people’s medical records from hackers.

Dr Luc Rocher, senior research fellow at Oxford University’s Internet Institute, who is not involved, said: “The scale and richness of NHS data required to train generative AI models makes ‘de-identifying’ such complex patient information notoriously challenging. De-identification carries a significant risk that patterns remain which could, inadvertently, lead back to individuals.

“Building powerful generative AI models for healthcare that protect patient privacy is an open, unsolved scientific problem. The very richness of data that makes it valuable for AI also makes it incredibly hard to anonymise. These models should remain under strict NHS control where they can be safely used.”

Dr Vin Diwakar, national director of transformation at NHS England, said: "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. This will boost our ability to move quickly towards personalised, preventative care."

Mr Kyle added: "This is work that will be instrumental to this Government's missions to overhaul healthcare and grow the economy, which sit at the heart of our Plan for Change. And an unrelenting focus on privacy and security means people can rest assured that their data is in safe hands."

The first stage of the Foresight programme is currently restricted to Covid-19-related research. Dr Tomlinson added: "We're looking at predicting Covid-19 outcomes - which may help us inform the next pandemic - but we're also testing the model's ability to generalise to other important healthcare outcomes, such as predicting the risk of hospitalisation or death in the next year, as well as the onset of over 1,000 different conditions.

"Ultimately, we'd like to increase the depth and capability of Foresight by including richer sources of data - information like physicians' notes and the results of investigations such as blood tests or scans."