Новый ИИ-инструмент ставит прогнозы по 1000 болезням на 10 лет вперед Translation: New AI Tool Predicts 1000 Diseases and Health Changes Over a Decade

Scientists have developed an AI tool capable of predicting over a thousand diseases and forecasting health changes up to a decade ahead.

Experts from the European Molecular Biology Laboratory (EMBL), the German Cancer Research Center, and the University of Copenhagen utilized algorithmic principles similar to those employed in large language models.

The AI was trained on data from two independent healthcare systems—using anonymized information from 400,000 individuals in the UK Biobank study and 1.9 million patients from Denmark’s national registry.

“Medical events often follow predictable patterns. Our AI model learns these patterns and can forecast future health outcomes,” stated Thomas Fitzgerald, a researcher at the European Bioinformatics Institute.

This new tool assesses the likelihood of an individual developing specific diseases and identifies when this is likely to occur. The neural network can predict cancer, diabetes, cardiovascular diseases, respiratory illnesses, and numerous other disorders.

The Delphi-2M model analyzes the patient’s medical history and lifestyle factors, including obesity, harmful habits, age, and gender.

Health risks are expressed in percentages over time, similar to a weather forecast: “There is a 70% chance of rain this weekend.”

Euan Birney, the acting director of EMBL, mentioned that patients will start benefiting from this tool in the coming years:

“You go for an appointment, and the doctor is already using such tools, saying, ‘Here are the four main risks for your future, and here are two things you can do to change that.’”

According to him, standard advice like losing weight or quitting smoking will still be relevant, but there will be more specific recommendations for certain diseases.

Birney emphasized that a key advantage of Delphi-2M over other solutions is its ability to predict all diseases simultaneously over an extended time frame.

“Delphi-2M assesses the probability of over 1,000 diseases based on individual medical histories, and its accuracy is comparable to existing models for specific diseases,” the project team stated.

Professor Moritz Gerstung, head of the AI department at the German Cancer Research Center, highlighted that Delphi-2M marks the beginning of a new understanding of human health and disease progression. He believes that generative models will eventually be able to personalize care and anticipate healthcare needs at the level of entire systems.

Recall that in September, researchers from Harvard Medical School introduced an AI model capable of identifying precise combinations of genes and drugs to reverse pathological conditions in human cells.