Прорыв в медицине: ИИ-модель может предсказывать риски более 1000 заболеваний на десятилетия вперед Breakthrough in Medicine: AI Model Can Predict Risks of Over 1000 Diseases for Decades to Come

Researchers have developed an AI tool capable of predicting over 1,000 diseases and forecasting health changes for up to 10 years 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 used 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 analyzes these patterns and can forecast future health outcomes,» said Thomas Fitzgerald, a researcher at the European Bioinformatics Institute.

This new tool assesses the likelihood that a person will develop a particular disease and when it might occur. The neural network can predict conditions such as cancer, diabetes, cardiovascular diseases, respiratory illnesses, and many other disorders.

The Delphi-2M model examines «medical events» in a patient’s history and lifestyle factors: body weight, harmful habits, age, and gender.

Health risks are expressed in percentages over time, similar to weather forecasts: «There’s a 70% chance of rain this weekend.»

Ewan Birney, acting director of EMBL, mentioned that patients will begin benefitting from the tool within the next few years:

«You come in for a check-up, and the doctor is already using such tools, saying: ‘Here are the top four risks for your future, and here are two things you can do to change that.'»

He acknowledged that standard advice like losing weight or quitting smoking is unavoidable, 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 period.

«Delphi-2M estimates the probability of over 1,000 diseases based on individual medical history, and its accuracy rivals that of existing models for specific diseases,» stated the project team.

Professor Moritz Gerstung, head of the AI department at the German Cancer Research Center, highlighted that Delphi-2M marks the beginning of a new way to understand human health and disease progression. He believes that generative models could one day personalize care and anticipate healthcare needs across entire systems.

As a reminder, 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.