{"id":99278,"date":"2025-05-13T23:13:15","date_gmt":"2025-05-13T23:13:15","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/99278\/"},"modified":"2025-05-13T23:13:15","modified_gmt":"2025-05-13T23:13:15","slug":"the-uk-just-trained-a-health-ai-on-57-million-people-to-predict-disease","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/99278\/","title":{"rendered":"The UK just trained a health AI on 57 million people to predict disease"},"content":{"rendered":"

\"Given <\/a>Given enough and the correct data, Foresight could predict patients\u2019 health trajectories. Credit: Wikimedia Commons<\/p>\n

The NHS (National Health Service) is the publicly funded healthcare system of the United Kingdom. Its main aim is to provide free medical care to residents at the point of use. But the NHS is also working on a very ambitious research project. <\/p>\n

Deep within secure data servers, a powerful new artificial intelligence model<\/a> has been quietly learning from the lives of nearly every person in the country. The model, called Foresight<\/a>, has been fed 10 billion fragments of medical history \u2014 from hospital visits and COVID-19 vaccinations to deaths \u2014 all drawn from the anonymized records of 57 million people.<\/p>\n

Its goal is to forecast future illness<\/a>, anticipate hospitalizations, and guide a sweeping shift from reactive to preventative healthcare.<\/p>\n

\u201cThis is the first time an AI model has been used within health research on 57 million people,\u201d said Angela Wood, a health-data scientist at the University of Cambridge, during a press briefing. \u201cThis is a real step forward.\u201d<\/p>\n

What Can Foresight See?<\/p>\n

Foresight builds on the same principles as ChatGPT<\/a>, using a large language model to learn patterns \u2014 but instead of completing sentences, it completes health trajectories.<\/p>\n

Initially developed in 2023 using GPT-3 and just 1.5 million NHS records from London, Foresight has massively grown in scope and sophistication. Its newest version is based on Meta\u2019s open-source LLaMA 2 model<\/a> and trained on eight national datasets spanning five years of health events.<\/p>\n

\"\" <\/a>AI-generated image.<\/p>\n

Dr. Chris Tomlinson, a health-data scientist at University College London and one of the model\u2019s creators, called it \u201cthe world\u2019s first national-scale generative AI model of health data.\u201d Speaking at the launch event, he emphasized its transformative potential: \u201cThe real potential of Foresight is to predict disease complications before they happen, giving us a valuable window to intervene early, and enabling a shift towards more preventative healthcare at scale.\u201d<\/p>\n

For example, he said, it might someday allow clinicians to predict a patient\u2019s risk of unscheduled hospitalization (a common precursor to serious deterioration) and take action before that decline begins. That action might include adjusting medications or targeting interventions based on subtle patterns in the data.<\/p>\n

The pilot study currently limits Foresight\u2019s use to COVID-19-related research. But even within this narrow scope, researchers are pushing the boundaries. For now, the model is in tests. Researchers want to see whether the model can predict over 1,000 conditions using past health records from 2018 to 2022.<\/p>\n

\u201cThat allows us to actually get as close to a ground truth as is possible,\u201d Tomlinson explained.<\/p>\n

Privacy, Power, and the Public<\/p>\n

The sheer scale of Foresight is both its strength and its greatest liability. It has access to a lot of data from a lot of people.<\/p>\n

Researchers have \u201cde-identified\u201d all the data used to train the. They\u2019ve removed names, birthdates, and addresses. Yet experts caution that anonymity at this scale can never be guaranteed. <\/p>\n

\u201cBuilding powerful generative AI models that protect patient privacy is an open, unsolved scientific problem,\u201d Luc Rocher, a data-privacy researcher at the University of Oxford told New Scientist<\/a>. \u201cThe very richness of data that makes it valuable for AI also makes it incredibly hard to anonymize. These models should remain under strict NHS control where they can be safely used.\u201d<\/p>\n

Patients cannot fully opt-out<\/a>. Those who have declined to share their GP records will be excluded. However, other data sources \u2014 hospital visits, vaccination records, national registries \u2014 are not covered by the opt-out. And once a model like Foresight is trained, it is impossible to remove an individual\u2019s record from the model\u2019s memory.<\/p>\n

Michael Chapman, director of data access at NHS England, acknowledged the concern. \u201cIt\u2019s very hard with rich health data to give 100 per cent certainty that somebody couldn\u2019t be spotted in that dataset,\u201d he said. Still, the AI is confined to a secure environment and supervised by NHS researchers. Even cloud providers like Amazon Web Services and Databricks, which supply the computing infrastructure, cannot access the data.<\/p>\n

Even Foresight\u2019s legal status remains a gray area. Under the UK\u2019s interpretation of GDPR, anonymized data isn\u2019t covered. But the Information Commissioner\u2019s Office warns against conflating \u201cde-identified\u201d with truly anonymous data.<\/p>\n

\"\u201cEven <\/a>\u201cEven if it is being anonymised, it\u2019s something that people feel very strongly about from an ethical point of view\u2026 the humans and the ethics need to be the starting point.\u201d said Caroline Green, a digital ethics researcher at Oxford. Credit: Wikimedia Commons<\/p>\n

A Microcosm of AI in Society<\/p>\n

This case study is an example of exactly how AI and society interact.<\/p>\n

If Foresight performs as its developers hope, it could mark a turning point in the way national health systems are managed. It could help clinicians personalize care with unprecedented precision and lag patients on the brink of crisis. But it puts a lot of private date at risk, and we\u2019re not entirely sure whether it will perform as hoped.<\/p>\n

\u201cThis technology is transforming what\u2019s possible in tackling a host of debilitating diseases,\u201d Kyle told The Independent<\/a>. \u201cFrom diagnosis, to treatment, to prevention.\u201d<\/p>\n

But the work is still in its early stages. Foresight is not yet making real-time predictions for patients. Researchers are still testing its accuracy across different demographics and disease types. Its ability to avoid privacy breaches is still unproven.<\/p>\n

Still, the long-term success of Foresight may depend less on its code and more on public trust<\/a>. If people believe their data is being used without consent, the project could lose the social license it depends on. In the race to harness AI in medicine, can the urgency of innovation be reconciled with the imperatives of ethics and accountability?<\/p>\n

That is a question we are yet to have any Foresight on.<\/p>\n","protected":false},"excerpt":{"rendered":"Given enough and the correct data, Foresight could predict patients\u2019 health trajectories. Credit: Wikimedia Commons The NHS (National…\n","protected":false},"author":2,"featured_media":99279,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4316],"tags":[39985,46112,105,4348,46113,46114,211,46115,46116,6512,16,46117,15],"class_list":{"0":"post-99278","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-healthcare","8":"tag-ai-in-healthcare","9":"tag-foresight-ai","10":"tag-health","11":"tag-healthcare","12":"tag-healthcare-innovation","13":"tag-medical-data","14":"tag-nhs","15":"tag-patient-data","16":"tag-preventive-medicine","17":"tag-privacy","18":"tag-uk","19":"tag-uk-health-system","20":"tag-united-kingdom"},"share_on_mastodon":{"url":"","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/99278","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=99278"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/99278\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/99279"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=99278"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=99278"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=99278"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}