Evaluation of Behavioural Changes Caused by Glucose Forecasts
Real-world data collected since the launch of the Diabits app in 2017 was evaluated to determine the effects of the Diabits app on users. A total of 9725 user days were evaluated with all available data. This data was collected over a period of 6 months and 10,368,000 CGM data points were compared to estimated values produced by the Diabits Predictions Engine. During this time, users did not report any instance of estimation inaccuracy, nor did they report any complications which may have been caused by the use of the app.
For any given day, a selection of results were calculated for each user including daily time-in-range (TIR), an HbA1c estimate, standard deviation (SD), high blood glucose index (HBGI) low blood glucose index (LBGI), and sessions-per-day (sessions).
Results were organized into bins for the average number of sessions in the day. In general, user’s statistics improve with increased use of the platform. Most notably, TIR and SD change substantially.