Scientists from the European Molecular Biology Laboratory (EMBL), the German Cancer Research Center and the University of Copenhagen have introduced Delphi-2M, a powerful AI tool capable of predicting the risk of more than a thousand diseases decades into the future. The system was trained on data from nearly 2.5 million patients in England and Denmark and takes into account diagnoses, lifestyle, age, sex and other factors.
A distinctive feature of Delphi-2M is its ability to build personal health scenarios that include both the probabilities and timing of disease onset. This gives doctors the chance to offer not general advice, but individualized prevention strategies. The forecast is presented in a clear form, like a weather forecast, with probability estimates.
In addition, the system can model virtual health trajectories 20 years ahead, helping to take long-term risks into account. The developers describe this as the beginning of a new era in medicine: an era of personalized prevention supported by artificial intelligence.
