£1.3m diabetes data study to spot signs of linked health problems
February 2017: This major research initiative will use cutting edge data analysis techniques to better understand the health complications that are experienced by people with diabetes.
Around 4 million people in the UK are living with diabetes, a lifelong health condition that occurs when the body is unable to regulate levels of sugar in the blood. In some people, it can lead to further health problems including heart disease, stroke and blindness. Estimates indicate the NHS spends around £14 billion each year treating the disease and its complications. Not all people with diabetes experience complications and the ability to identify those most at risk is currently limited.
The £1.3m research programme at the University of Edinburgh is being supported by the AXA Research Fund. It aims to identify symptom patterns that might indicate if people with diabetes are likely to develop complications, such as heart disease or blindness. Patients could then be offered therapies to prevent or delay their illness. The programme, which looks at both type 1 and type 2 diabetes, aims to improve care offered to patients and ultimately reduce strain on medical resources.
The project is being led by Professor Helen Colhoun, AXA Chair in Medical Informatics and Life Course Epidemiology at the Institute of Genetics and Molecular Medicine, The University of Edinburgh, who said:
"Quantifying, understanding and predicting risk in diabetes is important to our ability to optimise disease management and prevention of complications. The research funding we have received will allow us to focus on this important aspect of diabetes research."
Researchers will securely access anonymised healthcare data from people with diabetes living in Scotland to investigate potential warning signs. The project will use the latest big data analysis techniques to spot patterns that could provide early indications of a complication. These insights will be used to develop computer algorithms that help predict which people are most at risk and likely to benefit from a targeted intervention.