AI could predict type 2 diabetes up to 10 years in advance

An artificial intelligence (AI) tool that analyses ECG readings during routine heart scans could identify people at risk of type 2 diabetes as much as ten years before they begin to develop the condition. The research, funded by us, was presented today at the American Heart Association's Scientific Sessions 2024, in Chicago.

The innovative technology could allow for early interventions, helping people take steps to reduce their risk of developing type 2 diabetes in future.

Around 5.6 million people in the UK are living with diabetes, and it is thought up to 1.2 million of those have the condition and are yet to be diagnosed. Type 2 diabetes and 'prediabetes' are diagnosed using a blood test. Early detection is vital in reducing risk of type 2 diabetes and its associated complications, which can include problems with the heart, eyes and feet.

Clearer picture of risk

The team, led by Dr Fu Siong Ng and Dr Arunashis Sau at Imperial College London, developed the AI-ECG Risk Estimation for Diabetes Mellitus (AIRE-DM) tool, using around 1.2 million ECGs from hospital records. Using data from the UK Biobank, they then validated the AI's ability to detect subtle changes in routine ECGs that could signify that someone might be at higher risk of type 2 diabetes, years before their blood sugar levels begin to rise.

AIRE-DM accurately predicted future risk in people of various ages, genders, ethnicities and socioeconomic backgrounds about 70% of the time. The researchers suggest it could help spot people who might otherwise not have been identified as likely to develop the condition.

When the team incorporated the AI predictions with genetic and clinical information, such as age and blood pressure, it improved the accuracy even further, providing an even clearer picture of risk.

AIRE-DM could also accurately assess data collected from single-lead ECGs, which are often used in wearable devices, indicating that it could in future be applied to millions of smart devices.

The AI will be piloted in the next year, and the researchers hope it could be rolled out in the NHS in the next few years.

An opportunity to intervene

Professor Bryan Williams, our Chief Scientific and Medical Officer, said: "This exciting research uses powerful artificial intelligence to analyse ECGs, revealing how AI can spot things that cannot usually be observed in routinely collected health data. This kind of insight could be a gamechanger in predicting future risk of developing type 2 diabetes, years before the condition begins.

"Type 2 diabetes is a rapidly growing health challenge that increases the risk of developing heart disease, however with the right support it is possible for people to reduce their risk of developing the condition. We look forward to seeing how this technology could be incorporated into clinical practice, providing an opportunity to intervene early to help reduce risk and even prevent type 2 diabetes and its associated complications, altogether."

The research is also supported by the NIHR Imperial Biomedical Research Centre, a translational research partnership between Imperial College Healthcare NHS Trust and Imperial College London.

Public link

Please use the above public link if you want to share this noodl on another website.