Artificial intelligence (AI) can use glucose spikes to predict if people are at risk of developing type 2 diabetes, latest research has claimed.
Scientists from Scripps Research have found that AI models are more effective at predicting type 2 diabetes compared to HbA1c – the test currently used to spot the condition.
By using continuous glucose monitor (CGM) data alongside an individual’s gut microbiome, physical activity, genetic information and diet, a new AI model can detect early signs of type 2 diabetes that are often missed by standard HbA1c tests.
- Common blood glucose test fails to detect nearly three quarters of gestational diabetes cases
- Poor sleep linked to elevated HbA1c in people with type 2 diabetes
- Popular 5:2 fasting diet beneficial for people with type 2 diabetes and obesity
Senior author Professor Giorgio Quer said: “We showed that two people with the same HbA1c score can have very different underlying risk profiles.
“By bringing in more data – how long glucose spikes take to resolve, what happens to glucose overnight, what the food intake is, and even what’s happening in the gut – we can start to tell who’s on a fast track to diabetes and who isn’t.”
Corresponding author Ed Ramos said: “Ultimately, the goal of this work is to get a better understanding of what is driving diabetes progression and how we can intervene earlier in the clinic.”
Exaggerated glucose spikes can be an early sign that the body is unable to manage sugar effectively.
More than 1,000 adults took part in this clinical trial by wearing a Dexcom G6 CGM for 10 days and tracking their food intake and exercise. In addition, each participant sent in samples of their blood, saliva and stool for testing.
Ed Ramos said: “This was a really pioneering effort in the remote clinical trial space. We had to design a study that participants could complete entirely on their own – from applying sensor to collecting and shipping biological samples – without ever visiting a clinic.
“That level of self-guided participation required a completely different kind of infrastructure than usual.”
- Managing body weight is key driver out of all lifestyle factors in reducing type 2 diabetes risk
- New study uncovers key muscle pathways behind insulin resistance in type 2 diabetes
- Brain thinning triggered by type 2 diabetes
For people with type 2 diabetes, it would take 100 minutes or more for blood sugar to decrease after a spike, much longer than it would do in healthier individuals, the study has reported.
Professor Quer has concluded: “Ultimately, this is about giving people more insight and control. Type 2 diabetes doesn’t just appear one day, it builds slowly, and we now have the tools to detect it earlier and intervene smarter.”
To read the study, click here.