Short-term prediction of future continuous glucose monitoring readings in type 1 diabetes: Development and validation of a neural network regression model

Background and objective: CGM systems are still subject to a time-delay, which especially during rapid changes causes clinically significant difference between the CGM and the actual BG level. This study had the aim of exploring the potential of developing and validating a model for prediction of future CGM measurements in order to overcome the time-delay. Methods: An artificial neural network regression (NN) approach were used to predict CGM values with a leadtime of 15 min. The NN were trained and internally validated on 23 million minutes of CGM and externally validated on 2 million minutes of CGM. The validation included data from 278 type 1 diabetes patients using three different CGM sensors. The NN performance were compared with three alternative methods, linear extrapolation, spline extrapolation and last observation carried forward. Results: The internal validation yielded a RMSE of 9.1 mg/dL, a MARD of 4.2 % and 99.9 % of predictions were in the A + B zone of the consensus error grid. The external validation yielded a RMSE of 5.9-11.3 mg/dL, a MARD of 3.2-5.4 % and 99.9-100 % of predictions were in the A + B zone of the consensus error grid. The NN performed better on all parameters compared to the two alternative methods. Conclusions: We proposed and validated a NN glucose prediction model that is potential simple to use and implement. The model only needs input from a CGM system in order to facilitate glucose prediction with a lead time of 15 min. The approach yielded good results for both internal and external validation.