Study explores ways to classify data from continuous glucose monitors

In a new study, researchers attempted to standardize the process of analyzing raw data from continuous glucose monitors to help patients better manage their diabetes.

The study was published in the journal, Health Data Science, and led by researchers from the National University of Singapore. According to the study, continuous glucose monitoring (CGM) allows patients to monitor and act on real-time changes to their glucose levels. While this data can lead to more personalized and timely interventions, when looked at as a whole, the raw data can be overwhelming to interpret. For this study, researchers categorized daily glucose trends to simplify the process and improve the accuracy of analyzing CGM data and improve patient care quality.

“We developed a way of reducing the complexity of continuous glucose measurements to a smaller, distilled set of measurements that encapsulate the most important aspects of a patient’s records,” said Sue-Anne Toh, MD, an author of the study and doctor with NOVI Health, Singapore, and the National University of Singapore in a statement. “In a use case, we demonstrated the existence of four ‘glucotypes,’ groups of patients whose glucose measurements display different dynamics across the course of the day.”

These glucotypes allow doctors to categorize their patient’s glucose patterns quickly and efficiently, providing more effective and precise care, according to the study. In addition, researchers said this process can be used in statistical analyses to see how lifestyle and pharmaceutical interventions effect certain glucotypes.

For future investigations, researchers plan to study how other variables such as meals and physical exertion impact specific glucotypes.