924-P: Pattern Mining of Trajectories of Glucose Values of Continuous Glucose Monitoring System by Artificial Intelligence in Type 2 Diabetes Patients

Background: Thanks to technological advancements for medical devices, we can measure glucose by the minute for weeks using a sensor called the continuous glucose monitoring (CGM) system. CGM is time-series data and has been available since devices with low measurement error appeared 10 years ago. CGM can be relied upon to help make treatment decisions. A major issue regarding CGM is clinical interpretation by physicians. Methods: CGM data were obtained by flush glucose monitoring system in 156 type 2 diabetes patients. We divided the patients into 2 groups by mean HbA1c levels during 6 months before getting CGM data. High HbA1c group (High) had their mean HbA1c levels with equal to or above 7% and below 9%. Low HbA1c group (Low) had their mean HbA1c levels with equal to or above 5% and below 7%. The patients with their HbA1c levels equal to or above 9% was excluded from this study. We conducted the experiment with manually created dataset that is designed for evaluating the performance of trajectory extraction. Artificial intelligence (AI) performed pattern mining of raw data of flush glucose in 4 to 8 sequential data sets. Results: Among 156 patients, there were 83 High group patients, while 58 patients were defined as Low group. We excluded 15 patients from this study due to high HbA1c levels, while there was no patient with HbA1c level below 5%. AI constructed 1292 patterns of glucose trajectories from CGM data. We found that 67 patterns were significantly different between High and Low groups 8p