Identification of blood glucose patterns in patients with type1 diabetes using continuous glucose monitoring and clustering techniques

OBJECTIVETo show that statistical techniques allow for obtaining a reduced number of four-hour glucose profiles that can identify any glucose behavior in patients with type1 diabetes mellitus. MATERIAL AND METHODSA retrospective study of 10 patients with type1 diabetes mellitus was conducted using data collected by continuous glucose monitoring. A data mining technique based on decision trees called CHAID (Chi-square Automatic Interaction Detection) was used to classify glucose profiles into groups using two decision criteria. These were: 1, the seven days of the week, and 2, different time slots, the day being divided into six sections of four hours each. Clustering was performed according to the glucose levels recorded using the statistically significant differences found. RESULTSSignificant differences (P