Study reveals AI insights can predict development of disease a decade in advance

The study predicted the development of conditions including Alzheimer’s and heart disease

Researchers from the University of Edinburgh, along with commercial collaborators Optima Partners and Biogen, have revealed that artificial intelligence (AI) insights can predict a person’s disease’s development a decade in advance.

Using AI and machine learning tools to identify protein patterns in the blood, researchers have been able to predict the development of conditions such as Alzheimer’s disease (AD), heart disease and type 2 diabetes (T2D) prior to diagnosis.

Combined, conditions including dementia, heart and circulatory disease and diabetes are estimated to affect nearly 13 million people living in the UK.

The study, published in Nature Aging and funded by Wellcome, analysed blood samples from the UK Biobank up to ten years after the blood sample measurements and identified protein patterns in the blood that were indicative of the development of AD, heart disease and T2D.

The team then tested whether the patterns could be used to diagnose conditions in the blood samples of a separate group of individuals whose data had not been used to create the protein patterns.

They discovered that the protein patterns improved prediction accuracy beyond traditional risk factors, including age, sex, lifestyle behaviours, cholesterol and other commonly measured clinical variables.

Researchers believe that being able to detect early warning signs for a broad set of conditions may lead to opportunities for early intervention and prevention.

Dr Chris Foley, managing director and chief scientist, Optima Partners, said: “More work is still needed to convert these findings for practical use in clinical settings. However, our discoveries set strong foundations for the inclusion of new risk prediction signatures to shed light on possible pathways and mechanisms that underlie diseases.”

In July, the Engineering and Physical Sciences Research Council (ESPRC) announced the launch of two new hubs being delivered by Imperial College London, the Universities of Cambridge and Birmingham, supported as part of a £106m investment from the ESPRC, the Biotechnology and Biological Research Council, the Medical Research Council and the National Institute for Health and Care Research, to transform early disease diagnosis in the UK.