Amnesty International can predict your future health – just like the weather

Scientists say artificial intelligence can predict people’s health problems for a decade from time to the future.

This technology has learned to discover patterns in individuals medical records to calculate the risks of more than 1,000 disease.

The researchers say it is similar to weather forecast that expects a 70 % rain opportunity – but for human health.

Their vision is to use the artificial intelligence model to discover patients at risk to prevent the disease and help hospitals to understand the demand in their area, years before time.

The model-which is called Delphi-2M-uses a technique similar to the known Chatbots of artificial intelligence such as ChatGPT.

AI Chatbots is trained to understand language patterns so that they can predict the sequence of words in a sentence.

Delphi-2M has been trained to find patterns in unknown medical records so that they can predict what follows and when.

It does not predict micro -dates, such as a heart attack on October 1, but instead the possibility of 1,231 is estimated.

“Thus, just like the weather, where we can get a chance of 70 % of the rain, we can do this for health care,” said to me, Professor Ewan Bernie, the temporary CEO of the European Molecular Biology Laboratory.

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

The artificial intelligence model was initially developed using UK’s unknown data – including acceptance in hospitals, GP records and lifestyle habits such as smoking – collected from more than 400,000 people as part of Biological bank research project in the United Kingdom.

Then the model was tested to see if its predictions were stacked using data from other vital banks participants, then with 1.9 million people of medical records in Denmark.

“It’s good, it’s really good in Denmark,” says Professor Bernie.

“If our model says it is one in 10 to 10 for the next year, it appears that it appears to be one in 10.”

The model is the best in predicting diseases such as type 2 diabetes, heart attacks and seizures that have a clear disease, rather than random events such as infections.

People are already shown on statin to lower cholesterol at the expense of the risk of a heart attack or stroke.

The artificial intelligence tool is not ready for clinical use, but the plan is to use it in a similar way, to discover patients at risk while there is an opportunity to intervene early and prevent disease.

This may include medications or specific lifestyle advice – such as people who are likely to have some liver disorders that benefit from reducing alcohol intake more than the general population.

Artificial intelligence can also help inform diseases and analyze all health care records in an area to expect demand – such as the number of heart attacks in the year in Norwich in 2030, to help in planning resources.

“This is the beginning of a new way to understand human health and the development of disease,” said Professor Moritz Gistong, Head of the Department of Artificial Intelligence in DKFZ, German Cancer Research Center.

He added: “Obstetric models such as our models can help allocate care and expect widespread health care needs.”

Artificial Intelligence Model, Described in the natural scientific magazineIt needs to improve and test before using it clinically.

There are also possible biases as it was built from the Data of the UK biological bank that is often extracted from people between the ages of 40 and 70 years, instead of all the population.

The model is now upgraded to calculate more medical data such as photography, genetics and blood analysis.

But Professor Bernie says: “Only to confirm, this is the research-everything must be tested and organized well and think about it before using it, but the technology is here to make these types of predictions.”

This is expected to follow a way similar to the use of genome in the field of health care, as it took a decade of time from technology confident scientists to health care the ability to use it routinely.

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

Professor Gustavo Soderi, a nervous photography researcher and AI at King’s College London, commented: “This research appears to be an important step towards an extensive, interpretable form, and most importantly – an ethical form of predictive modeling in medicine.”