news-medical.net
A new AI-based tool developed at Stanford Medicine offers a promising method to improve diabetes classification by identifying distinct subtypes using continuous glucose monitors.
This advancement can significantly enhance personalized treatment strategies by allowing healthcare providers to tailor interventions to specific metabolic profiles.
Researchers at Stanford Medicine have introduced an AI-enhanced algorithm capable of using continuous glucose monitor data to distinguish between subtypes of Type 2 diabetes. This could revolutionize diabetes care by enabling tailored treatment, benefiting around 13% of the U.S. population diagnosed with diabetes.
Diabetes, traditionally categorized as Type 1 or Type 2, is now known to be more complex. Recent research has unveiled distinct subtypes among Type 2 diabetes patients, influenced by varying physiological factors such as insulin resistance and beta-cell dysfunction. This knowledge calls for a departure from generalized treatment approaches in diabetes management.
"The majority of people with diabetes have Type 2, and they're just called 'Type 2.' But it's more complex than that," said Tracey McLaughlin, MD, professor of endocrinology. "Our goal was to find a more accessible, on-demand way for people to understand and improve their health."
Stanford Medicine's use of artificial intelligence has enabled the detection of distinct glucose patterns that correlate with diabetes subtypes. By analyzing continuous glucose monitor data, an AI algorithm identifies peaks and troughs unique to subtypes like insulin resistance or beta-cell deficiency, achieving an accuracy of 90%.
"People have looked at that for decades and have found certain parameters that indicate insulin resistance or beta cell dysfunction, which are the main drivers of diabetes," noted McLaughlin. "But now we have the monitors, and you can get a much more nuanced picture of the glucose pattern which predicts these subtypes with greater accuracy and can be done at home."
Recognizing the subtypes among Type 2 diabetes patients allows for more precise therapeutic interventions, which is a significant shift from traditional treatment models. This approach can better address associated conditions, such as cardiovascular and liver diseases, tailored to the individual's metabolic profile.
According to McLaughlin, even without developing diabetes, knowing about insulin resistance helps manage risks related to heart and liver diseases. The broader availability and accessibility of this technology might democratize healthcare, providing benefits to those in rural or underserved communities.
"We also see this technology as a valuable health care tool for people who are economically challenged or geographically isolated and can't access a health care system," said McLaughlin.