Diagnosing Diabetes Needs Better Tools. They are on the Way

Over the years, a diabetes disease has become very dependent measure sugar I feel like it’s beyond the medical limit. But researchers are deeply concerned that this method is missing out on millions of people to the disease.

All over the world, diabetes has become one of the most recognized problems today. According to the World Health Organization, 14 percent of adults will have diabetes in 2022, up from 7 percent in 1990. In the US, more than 40 million people have diabetes, but about 11 million remain undiagnosed. More than 115 million Americans are comparison have diabetes, and about 80 percent do not know it. In the UK, around 5.8 million people have diabetes, with over 1.3 million people thought to be undiagnosed.

“We are talking about an epidemic that, in my opinion, is much worse than the Covid epidemic,” said Michael Snyder, a professor of genetics at Stanford University. “We need new ways to do this.”

The danger is not only diabetes, but also the damage that accumulates silently for many years before being noticed. High blood sugar increases the risk of heart disease, stroke, kidney failure, blindness, and nerve damage. The earlier the disease is detected, the greater the chance of preventing complications or preventing diabetes altogether.

Diagnosis still relies heavily on measuring blood sugar, usually using the HbA1c test, which measures average blood sugar over the past few months. Although they are widely used and reliable, they are not infallible. The results cannot indicate other medical or physical problems that may affect blood sugar levels.

Researchers are increasingly concerned that existing screening tools may not work in some populations. Recent studies give suggestions HbA1c can be misdiagnosed in some black and South Asian people, delaying diagnosis until the disease is more advanced.

This disparity has fueled interest in the pursuit of more intuitive and quantitative methods of diagnosing diabetes: those that combine biomarkers, wearables, and artificial intelligence to predict events and understand the disease in detail.

At Stanford University, Snyder and his colleagues have been investigating whether continuous glucose monitors (CGMs) – wearable sensors that track blood glucose levels in real time – can reveal hidden metabolic pathways before they are diagnosed with type 2 diabetes, which accounts for about 95 percent of cases. Although obesity is often the cause—the main cause of the disease—underweight people can also develop type 2 diabetes.

“Glucose control affects many organ systems: the liver, muscles, intestines, pancreas, and even the brain,” says Snyder. “There are many ways to treat diabetes, and it’s clear that reducing sugar can’t be just one container.”

The Stanford team developed an AI-powered algorithm that analyzes CGM data to identify different types of diabetes. In tests, the system identified some of these features with an accuracy of about 90 percent.

The researchers believe that their findings may help identify pre-diabetes patients before they are diagnosed with diabetes. “It’s a tool that people can use for prevention,” Snyder says. “If the levels trigger a prediabetes warning, diet or exercise can be changed, for example.”

CGMs are also becoming more affordable and accessible, and many are now available over the counter in the US. Snyder believes he can eventually become part of a defensive defense. “In this beautiful world, people wear it once a year,” he said.