Scottish researchers use AI to predict Alzheimer's, diabetes and heart disease risk 10 years early

Scottish scientists have made a “significant” breakthrough that could predict a person’s risk of disease up to ten years before a diagnosis - including Scotland’s biggest killers.

Researchers from the University of Edinburgh, along with Biogen and Optima Partners, have used AI to identify protein markers in biological samples which are linked to Alzheimer’s, type 2 diabetes, and heart disease.

In Scotland, ischaemic heart disease accounts for more deaths than any other pathology - accounting for more than one in ten deaths in 2022.

The study analysed data from a randomised set of almost 50,000 individuals who had a blood sample taken between 2006 and 2010.

The machine-learning AI was used to analyse a vast amount of medical data stored in the UK Biobank. This allowed the researchers to accurately predict a person’s risk of disease up to ten years before diagnosis.

The research also showed how results from currently used patient blood tests could be compared with new protein patterns discovered in Biobank data.

In theory, this would allow clinicians to detect the possibility of a particular disease developing later in life.

If tests show a patient is at higher risk, there will be more time to proactively plan and take preventative measures to improve the eventual patient outcome.

Dr Danni Gadd, the first author of the study.

The study analysed data from a randomised set of almost 50,000 individuals who had a blood sample taken between 2006 and 2010.

Scientists were then able to improve the prediction for disease outcomes diagnosed, up to 15 years after the initial blood sample was taken.

Dr Danni Gadd, the first author of the study, said: “Our research represents a promising step forward in risk prediction.

“It’s encouraging to see how much potential there is from a single blood sample that allows us to predict a range of disease outcomes.

“Being able to detect early warning signs for a broad set of conditions may lead to opportunities for early intervention and prevention, marking a significant moment for the healthcare industry.”

GDF15, a marker of inflammation, was among some of the proteins under investigation and was found to be linked with almost half (eleven out of 23) of the diseases being studied, including both Alzheimer’s and vascular dementia, heart disease, liver disease, type 2 diabetes and all-cause mortality.

One of the study’s principal investigators, Dr Chris Foley, managing director and chief scientist of 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 a light on possible pathways and mechanisms that underlie diseases.

“Pattern recognition like this would not be possible without modern machine learning technology and its capacity to analyse data at this scale and will in turn allow us to address some of the most pressing healthcare challenges of our time.”

The latest figures from the Scottish Diabetes Survey in 2022 show that there are almost 340,000 people in Scotland with a diagnosis of diabetes.

Approximately 88 per cent are living with type 2 diabetes, around ten per cent are living with type 1, and two per cent with the other forms of the condition.

John Kinnear, the national director of Diabetes Scotland said: “Diabetes is serious, and every diagnosis is life changing.

“It’s a relentless condition, and the fear of serious complications is a lifelong reality for people across Scotland.

“The latest Scottish Diabetes Survey figures show we’re in the grip of an escalating diabetes crisis, with rapidly increasing numbers of people now living with type 2 diabetes and millions at risk of developing the condition.

“These findings suggest that certain markers in the blood might help to more accurately predict who is at risk of developing type 2 diabetes.

“We welcome further research into type 2 diabetes predictive tools, as the earlier people at high risk are identified, the greater the opportunity to help them reduce their risk.”

Mr Kinnear added that research has consistently shown that for some people combined interventions – including diet, physical activity and sustained weight loss – can be effective in reducing the risk of type 2 diabetes by about 50 per cent.

“In Scotland, we are working for a comprehensive plan to tackle obesity and the rise of type 2 diabetes,” he said,

“This includes calling for changes to our food environment to reduce salt, sugar and saturated fat and increased long-term investment in targeted support programmes for those most at risk of diabetes like Healthier Future, Scotland’s diet and healthy weight delivery plan.”

The Scottish Government estimates that 90,000 people in Scotland have dementia, while the World Health Organisation estimates that 60-70 per cent of people with dementia have Alzheimer’s.

Alzheimer Scotland’s deputy chief executive, Jim Pearson, said: “Alzheimer Scotland welcomes the results of this research and the prospect of having a reliable tool to identify those at increased risk of dementia and other illnesses.

“Predicting individual risk offers a valuable opportunity to support people to develop and implement their own risk reduction plans.

“There’s an established evidence base that shows up to 40 per cent of dementia cases could be preventable.

“This is based on a number of modifiable risk factors, such as taking regular exercise, staying socially connected and reducing risks related to alcohol and smoking.

“We look forward to seeing how this initiative develops and hope further work can be done to make it available for practical use in clinical settings.”

The study was published in the journal Nature Aging and was conducted by researchers from Optima Partners, Biogen and the University of Edinburgh.