Artificial intelligence can predict people's health problems over a decade into the future, say scientists.
The technology has learned to spot patterns in people's medical records to calculate their risk of over 1,000 diseases.
Researchers envision using the AI model to identify high-risk patients, helping to prevent diseases and assisting hospitals in understanding demand in their areas well in advance.
The model, Delphi-2M, utilizes technology similar to popular AI chatbots. It analyzes anonymous medical records to predict health events, offering estimates of disease risks rather than specific dates.
According to Prof Ewan Birney from the European Molecular Biology Laboratory, this innovative approach could transform how healthcare anticipates and addresses potential health crises.
The AI model was developed using data from the UK Biobank project, specifically examining records from more than 400,000 participants. Its accuracy has been validated through additional data sets from Denmark, yielding promising results in predicting health outcomes.
While the AI tool is not ready for clinical use yet, the researchers aim to utilize it for early intervention and personalized healthcare strategies.
This breakthrough could pave the way for more accurate disease-screening programs and improved healthcare resource planning.