ИИ-модель Delphi-2M предсказывает здоровье и болезни на десять лет вперед Translation: Headline: AI model Delphi-2M predicts health and diseases ten years ahead.

Researchers have created an AI tool capable of predicting over 1,000 diseases and forecasting health changes up to a decade in advance.

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

The AI was trained on data from two independent healthcare systems: 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 studies these patterns and can forecast future health outcomes,» stated Thomas Fitzgerald, a researcher at the European Bioinformatics Institute.

The new tool assesses the likelihood of an individual developing various diseases and the timing of such developments. The neural network can predict cancer, diabetes, cardiovascular diseases, respiratory illnesses, and numerous other disorders.

The Delphi-2M model evaluates «medical events» in a patient’s history alongside lifestyle factors such as weight, harmful habits, age, and gender.

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

Acting EMBL Director Ewan Birney remarked that patients will start benefiting from this tool in the near future:

«You arrive for an appointment, and the doctor is already utilizing such tools, saying, ‘Here are the four main risks for your future, along with two actions you can take to change that.'»

He acknowledged that standard advice like losing weight or quitting smoking will still be relevant, but for some diseases, there will be more specific recommendations.

Birney highlighted that a key advantage of Delphi-2M over other solutions is its capability to predict all diseases simultaneously over an extended timeframe.

«Delphi-2M evaluates the likelihood of more than 1,000 diseases based on an individual’s medical history, with accuracy 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, emphasized that Delphi-2M marks the beginning of a new approach to understanding human health and disease progression. He suggested that generative models could eventually personalize care and predict healthcare needs on a system-wide scale.

Additionally, in September, researchers from Harvard Medical School unveiled an AI model capable of identifying precise gene and drug combinations to reverse pathological conditions in human cells.