Scientists in a recent breakthrough have developed a new artificial intelligence (AI) tool that is capable of forecasting the risks of more than 1000 diseases up to 10 years ahead.
The generative tool named Delphi-2M was built by researchers from the European Molecular Laboratory (EMBL), the University of Copenhagen, and the German Cancer Research Centre by utilizing large language models-based algorithms.
According to study findings published in Nature journal, the new generative AI tool can find out the risks related to heart conditions, cancers more than a decade early.
Delphi-2M model brings out diagnosis based on the lifestyle factors and medical events that occurred in the patient's life history.
The game-changing tool has been trained and trialled on anonymised patient data from 400,000 people in the UK Biobank study and 1.9 million patients in Denmark.
Moritz Gerstung, head of the AI in oncology team at the German Cancer Research Centre (DKFZ), said in a statement, “This is the beginning of a new way to understand human health and disease progression.”
According to the research team, “Delphi-2M predicts the rates of more than 1,000 diseases, conditional on each individual’s past disease history, with accuracy comparable to that of existing single-disease models.”
“Delphi-2M’s generative nature also enables sampling of synthetic future health trajectories, providing meaningful estimates of potential disease burden for up to 20 years,” they added.