Washington: artificial intelligence Can be used to turn a continuous glucose monitor (CGM) into a powerful tool Diabetes Monitoring And prevention, suggest researchers at Click Applied Science.
In findings presented at the NeurIPS conference in New Orleans, the Klick scientists revealed how they used machine learning and just 12 hours of data from a CGM to determine whether a patient is pre-diabetic or diabetic.
“We have shown that 12-hour monitoring can make a big difference in the lives of people at risk of developing diabetes, while still being timed,” said Johyun Jeon, the study’s lead scientist and principal investigator of Click Applied Science. “We think CGM can be used not only to monitor diabetes but to prevent it altogether.”
For the study, about 600 patients who were healthy, pre-diabetes or living with type 2 diabetes wore the CGM device for an average of 12 days. The scientists looked at their glucose measurements over time and developed a machine learning model to see if those values could be used to determine whether a person was healthy, pre-diabetic or diabetic.
Jeon said they found that their 12-hour model showed the same high accuracy as long-term results, correctly identifying two-thirds of patients with prediabetes, while also showing high accuracy in identifying healthy patients and patients with type 2 diabetes. Jeon said the shorter time frame is a big step forward, with most research adding up to 10 to 14 days worth of readings and often requiring analysis from specialist clinicians.
According to the CDC, prediabetes is a serious health condition where blood sugar levels are higher than normal, but not yet high enough to be diagnosed as type 2 diabetes. About 96 million American adults–more than one in three–have prediabetes. Of those with prediabetes, more than 80 percent don’t know they have it.
“Most people with early-onset diabetes are unaware of their condition and do not seek medical attention until their ability to control their blood sugar levels is overwhelmed,” said Michael Lieberman, managing director of research and development at CLICK. Applied Science. “Our research has tremendous potential to help move digital biomarkers of blood glucose to a position where they can be an invaluable tool for clinicians to prevent diabetes before it starts.”
These findings are the latest in Click’s ongoing work in the diabetes space. Their study, “Homeostasis as a Proportional-Integral Control System,” based on mathematical modeling to determine some of the underlying changes in how glucose is regulated that can cause diabetes, was published in Nature in 2020. They also presented earlier findings at the 2018 International. Joint Conference on Artificial Intelligence (IJCAI) in Stockholm, Sweden.
