Search
Close this search box.

Study Reveals AI Tool Predicts Long-Term Risk of Over 1,000 Diseases

Manila: A new artificial intelligence (AI) tool, Delphi-2M, is reportedly capable of forecasting an individual’s risk of developing more than 1,000 diseases, potentially projecting outcomes decades into the future. This development was highlighted in a recent study published in the scientific journal Nature.

According to Philippines News Agency, the modified language model, Delphi-2M, utilizes health records and lifestyle factors to estimate the likelihood of conditions such as cancer, skin diseases, and immune disorders up to 20 years in advance. The tool is designed to model multiple diseases, which may enable healthcare providers to identify high-risk individuals and implement preventive measures earlier than previously possible.

Unlike earlier AI tools that focused on predicting the risk of individual diseases such as cancer or cardiovascular conditions, Delphi-2M has been enhanced to forecast the likelihood of a person developing 1,258 diseases. This prediction is based on a comprehensive analysis of an individual’s medical history, factoring in age, sex, body mass index, and lifestyle choices, including smoking and alcohol consumption.

For most diseases, Delphi-2M either outperformed or matched the accuracy of existing single-disease risk models. The development and validation of the tool were achieved using anonymized data from 400,000 participants in the UK Biobank and 1.9 million patients in Denmark’s national patient registry.