James Gallagher<\/span>Health and science correspondent<\/span><\/p>\n <\/span><\/div>\n<\/div>\n Artificial intelligence can predict people’s health problems over a decade into the future, say scientists.<\/p>\n The technology has learned to spot patterns in people’s medical records to calculate their risk of more than 1,000 diseases.<\/p>\n The researchers say it is like a weather forecast that anticipates a 70% chance of rain \u2013 but for human health.<\/p>\n Their vision is to use the AI model to spot high-risk patients to prevent disease and to help hospitals understand demand in their area, years ahead of time.<\/p>\n<\/div>\n The model \u2013 called Delphi-2M – uses similar technology to well-known AI chatbots like ChatGPT.<\/p>\n AI chatbots are trained to understand patterns of language so they can predict the sequence of words in a sentence.<\/p>\n Delphi-2M has been trained to find patterns in anonymous medical records so it can predict what comes next and when.<\/p>\n It doesn’t predict exact dates, like a heart attack on October 1, but instead estimates the likelihood of 1,231 diseases.<\/p>\n “So, just like weather, where we could have a 70% chance of rain, we can do that for healthcare,” Prof Ewan Birney, the interim executive director of the European Molecular Biology Laboratory, told me.<\/p>\n “And we can do that not just for one disease, but all diseases at the same time – we’ve never been able to do that before. I’m excited,” he said.<\/p>\n<\/div>\n The AI model was initially developed using anonymous UK data – including hospital admissions, GP records and lifestyle habits such as smoking – collected from more than 400,000 people as part of the UK Biobank research project.<\/p>\n The model was then tested to see if its predictions stacked up using data from other Biobank participants, and then with 1.9 million people’s medical records in Denmark.<\/p>\n “It’s good, it’s really good in Denmark,” says Prof Birney.<\/p>\n “If our model says it’s a one-in-10 risk for the next year, it really does seem like it turns out to be one in 10.”<\/p>\n The model is best at predicting diseases like type 2 diabetes, heart attacks and sepsis that have a clear disease progression, rather than more random events like infections. <\/p>\n<\/div>\n People are already offered a cholesterol-lowering statin based on a calculation of their risk of a heart attack or stroke.<\/p>\n The AI tool is not ready for clinical use, but the plan is to use it in a similar way, to spot high-risk patients while there is an opportunity to intervene early and prevent disease. <\/p>\n This could include medicines or specific lifestyle advice – such as people likely to develop some liver disorders benefitting from cutting back their alcohol intake more than the general population. <\/p>\n The artificial intelligence could also help inform disease-screening programmes and analyse all the healthcare records in an area to anticipate demand – such as how many heart attacks a year there will be in Norwich in 2030, to help plan resources.<\/p>\n “This is the beginning of a new way to understand human health and disease progression,” said Prof Moritz Gerstung, head of the division of AI in oncology at DKFZ, the German Cancer Research Centre.<\/p>\n He added: “Generative models such as ours could one day help personalise care and anticipate healthcare needs at scale.”<\/p>\n<\/div>\n The AI model, described in the scientific journal Nature, needs refining and testing before it is used clinically. <\/p>\n There are also potential biases as it was built from UK Biobank data which is drawn mostly from people aged 40 to 70, rather than the whole population. <\/p>\n The model is now being upgraded to account for more medical data such as imaging, genetics and blood analysis.<\/p>\n But Prof Birney says: “Just to stress, this is research \u2013 everything needs to be tested and well-regulated and thought about before it’s used, but the technology is here to make these kinds of predictions.”<\/p>\n He anticipates it will follow a similar path to the use of genomics in healthcare where it took a decade to go from scientists being confident in the technology to healthcare being able to use it routinely. <\/p>\n The study was a collaboration between the European Molecular Biology Laboratory, the German Cancer Research Centre (DKFZ) and the University of Copenhagen.<\/p>\n Prof Gustavo Sudre, a neuroimaging and AI researcher at King’s College London, commented: “This research looks to be a significant step towards scalable, interpretable, and \u2013 most importantly \u2013 ethically responsible form of predictive modelling in medicine.”<\/p>\n<\/div>\n<\/div>\n![\"Jeff](\"https:\/\/ichef.bbci.co.uk\/news\/480\/cpsprodpb\/3f91\/live\/56711b40-93a7-11f0-afac-7fc88e0d02fd.jpg.webp\")
Jeff Dowling\/EMBL-EBI<\/span><\/div>\n<\/div>\n![](\"https:\/\/static.files.bbci.co.uk\/bbcdotcom\/web\/20250905-110137-f27f908f49-web-2.29.1-3\/grey-placeholder.png\")
![\"Jeff](\"https:\/\/ichef.bbci.co.uk\/news\/480\/cpsprodpb\/476d\/live\/80f9a030-93a7-11f0-afac-7fc88e0d02fd.jpg.webp\")
Jeff Dowling\/EMBL-EBI<\/span><\/div>\n<\/div>\nWhat can you do with the results?<\/h2>\n<\/p>\n