AI can predict your future health – just like the time

Artificial intelligence can predict people’s health problems for a decade in the future, scientists say.

The technology has learned to detect models in medical records of people to calculate the risk of more than 1000 diseases.

Researchers say this is like a time forecast, which provides for a 70% chance of rain – but for human health.

Their vision is to use the AI ​​model to detect high -risk patients to prevent the disease and help hospitals understand the demand in their area years before.

The Delphi-2M-Used Model uses a similar technology for well-known AI chatbots such as Chatgpt.

AI chatbots are trained to understand the models of the language so that they can predict the sequence of words in a sentence.

Delphi-2M is trained to find models in anonymous medical records so that he can predict what follows and when.

This does not provide accurate dates such as a heart attack on October 1, but instead evaluates the likelihood of 1.231 diseases.

“So, just like the time we could have a 70% chance of rain, we can do this for healthcare,” Prof. Evan Bryni, the temporary executive director of the European Laboratory for Molecular Biology, told me.

“And we can do this not only for one disease, but all the diseases at the same time – we have never been able to do it before. I am excited,” he said.

The AI ​​model was originally developed with the help of anonymous UK data – including hospital intake, GP records and lifestyle habits such as smoking – collected by more than 400,000 people as part of United Studies in UKS

The model was then tested to see if its forecasts were arranged using data from other Biobank participants, and then with 1.9 million medical records in Denmark.

“It’s good, it’s really good in Denmark,” says Prof. Berni.

“If our model says this is a risk one in 10 for next year, it really looks like it turns out to be one in 10.”

The model is best in predicting diseases such as type 2 diabetes, heart attacks and sepsis, which have a clear progression of the disease, and no more accidental events such as infections.

People are already offered a statin-inflating cholesterol based on the calculation of the risk of heart attack or stroke.

The AI ​​tool is not ready for clinical use, but the plan is to use it similarly to detect high -risk patients while it is possible to intervene early and prevent disease.

This may include medicines or specific lifestyle tips – such as people who are likely to develop some liver disorders that benefit from reducing alcohol intake more than a general population.

Artificial intelligence can also help inform disease shielding programs and analyze all healthcare records in an area to predict the search – for example, how many heart attacks will be in Norich in 2030 to help plan resources.

“This is the beginning of a new way of understanding human health and the progression of diseases,” says Prof. Moritz Gerstung, Head of the AI ​​Department of Oncology at DKFZ, the German Cancer Research Center.

He added: “General models like ours can one day help customize care and predict health needs on a scale.”

The AI ​​model, Described in the scientific magazine of natureneeds refining and testing before using clinically.

There are also potential bias because they were made up of BIOBANK data from the UK, who are most involved in people aged 40 to 70, not the whole population.

The model is now upgraded to account for more medical data such as images, genetics and blood analysis.

But prof.

He provides that this will follow a similar path to using genomics in healthcare, where it takes a decade to go by scientists who are confident in technology so that healthcare can use it routinely.

The study is a cooperation between the European Laboratory in Molecular Biology, the German Cancer Research Center (DKFZ) and the University of Copenhagen.

Prof. Gustavo Sudre, a researcher in neurosualization and AI by King’s College London, commented: “This research seems to be a significant step towards scales, interpretive and – most importantly, an ethically responsible form of forecast modeling in medicine.”