Scientists have developed a method that uses artificial intelligence to predict the onset of diabetes within 12 hours

Scientists at Klick Applied Sciences have discovered a way
to use artificial intelligence to turn continuous glucose monitors (CGMs) into powerful diabetes screening and prevention tools.

In findings presented at Friday's NeurIPS conference in New Orleans, Klick's scientists revealed how they used machine learning and 12-hour data from CGMs to determine whether a patient is pre-diabetic or diabetic
.

Jouhyun Jeon, lead scientist of the study and principal investigator at Klick Applied Sciences, said: "We have shown that 12 hours of monitoring can make a big difference in the lives of those at risk of developing diabetes, and they still have time to correct.
"
"We believe that CGM can be used not only to monitor diabetes, but to prevent it completely
.
"

In the study, about 600 healthy, pre-diabetic or type 2 patients wore CGM devices for an average of 12 days
.
The scientists looked at their blood sugar measurements over time and developed machine learning models to see if the numbers could be used to determine whether the person was healthy, pre-diabetic or diabetic
.

Jeon said they found that their 12-hour model had similar accuracy to the results at longer intervals, correctly identifying two-thirds of people with prediabetes, while also showing high accuracy
in identifying healthy patients and those with type 2 diabetes.
The shorter time frame is a big improvement, Jeon said, adding that most studies are 10- to 14-day readings that often require analysis by expert
clinicians.

According to the Centers for Disease Control and Prevention, prediabetes is a serious health condition in which a patient's blood sugar levels are higher than normal but not high enough to be diagnosed with type 2 diabetes
.
About 96 million U.
S.
adults — more than one-third — have prediabetes
.
Of those with prediabetes, more than 80 percent don't know they have diabetes
.

"The vast majority of people with early-onset diabetes are unaware of their condition and don't go to the doctor until their ability to control blood sugar levels is irreparably damaged," said
Michael Lieberman, managing director of research and development at Klick Applied Sciences.
"Our study has tremendous potential to help transfer blood glucose digital biomarkers to one location, making it an invaluable tool
for physicians to prevent diabetes before it occurs.
"

These findings are the latest in Klick's ongoing research in the field of diabetes
.
Their "Endostasis as a Proportional Integral Control System" study, based on mathematical modeling to identify some potential changes in the way glucose is regulated that could lead to diabetes, was published in Nature in 2020
.
They also unveiled their earlier findings
at the 2018 International Joint Conference on Artificial Intelligence (IJCAI) in Stockholm, Sweden.