Diabits, a smartphone app that helps patients with diabetes monitor and manage their blood glucose levels in real time, appears to accurately predict future glycemic fluctuations, according to a study published in JMIR Diabetes. With continuous glucose monitoring (CGM) devices relaying their output to smartphone apps, providing users with real-time information on their glycemic fluctuations and possibly predicting future trends, researchers sought to discuss various challenges of predictive monitoring of glycemia and examine the accuracy and blood glucose control effects of Diabits, a smartphone app that uses data from CGM devices and user input, applying machine learning techniques to create personalized patient models and predict blood glucose fluctuations up to 60 min in advance. For the retrospective observational cohort study, the predictive accuracy of Diabits and the correlation between daily use of the app and blood glucose control metrics were examined based on real app users’ data. Accuracy of predictions on the 2018 Ohio T1DM (type 1 diabetes mellitus) data set was calculated and compared against other published results. On the basis of more than 6.8 million data points, 30-min Diabits predictions evaluated using Parkes Error
Grid were found to be 86.89% clinically accurate and 99.56% clinically acceptable, while 60-min predictions were 70.56% clinically accurate and 97.49% clinically acceptable. Upon analyzing daily use statistics and CGM data for the 280 most longstanding users of the app, the study team determined that many common blood glucose control metrics improved, under free-living conditions, with increased frequency of app use. For days with 10 or more Diabits sessions, average blood glucose decreased to 141.6 mg/ dL, while time in euglycemic range increased
to 74.28%.
