England’s NHS is launching a world-first trial of a transformative artificial intelligence (AI) tool that can identify patients at risk of type 2 diabetes at much as 13 years before they develop the condition.
The technology analyses electrocardiogram (ECG) readings during routine heart scans, detecting subtle changes too small to be noticed by the human eye that could raise the alarm early about a patient on the road to getting type 2 diabetes.
It could enable early interventions and potentially help people avoid developing the condition altogether by, for example, making changes to their diet and lifestyle.
The NHS will begin trialling the tool in 2025 at Imperial College healthcare NHS trust and Chelsea and Westminster hospital NHS foundation trust, and will be the first healthcare system in the world to do so, The Guardian reports.
Those involved in developing the technology, called the AI-ECG risk estimation for diabetes mellitus (Aire-DM), hope to roll it out across the health service in England and in other countries within the next few years.
“AI holds enormous potential to transform care that could lead to substantial improvements in health,” said Dr Libor Pastika, a clinical research training fellow at Imperial.
“Offering a cheap, accessible, non-invasive way to predict type 2 diabetes risk early, Aire-DM could open up a new window of opportunity for more targeted, preventive care, helping people avoid the condition and its associated complications.”
A team led by Dr Fu Siong Ng and Dr Arunashis Sau at Imperial developed the tool using 1.2m ECGs from hospital records. They then used data from the UK Biobank, which holds the genetic data and medical records of more than 500 000 participants, to validate the tool’s ability to detect subtle changes in ECGs.
The tool maps tiny ECG patterns more common in those who will go on to develop type 2 diabetes in the future – and then looks for those same patterns in new ECGs.
The telltale signs include variations in how the heart’s electrical signal travels, such as small changes in the timing, shape, or patterns of certain electrical waves.
The tool can also identify longer electrical activation times or differences in the way the heart’s electrical signals reset. While these changes may seem minor, they reflect early effects of diabetes on the heart’s structure and function, well before symptoms appear.
Tests have already shown the tool accurately predicts risk about 70% of the time.
See more from MedicalBrief archives:
Global study finds new genetic risk factors for type 2 diabetes
New review highlights diabetes research, treatment advances
Diabetes a leading killer in SA, but we don’t know how many have it