Department of Health Science and Technology, Aalborg University, Denmark.
Department of Health Science and Technology, Aalborg University, Denmark; Steno Diabetes Center North Denmark, Aalborg University Hospital, Aalborg, Denmark.
Int J Med Inform. 2021 Jul;151:104472. doi: 10.1016/j.ijmedinf.2021.104472. Epub 2021 Apr 24.
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.
An artificial neural network regression (NN) approach were used to predict CGM values with a lead-time 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.
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.
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.
CGM 系统仍存在时间延迟，尤其是在血糖快速变化时，CGM 与实际血糖水平之间会出现临床显著差异。本研究旨在探索开发和验证预测未来 CGM 测量值模型的潜力，以克服时间延迟。
采用人工神经网络回归（NN）方法，预测 15 分钟提前期的 CGM 值。NN 在 2300 万分钟的 CGM 数据上进行训练和内部验证，并在 200 万分钟的 CGM 数据上进行外部验证。验证包括来自 278 名 1 型糖尿病患者的数据，使用了三种不同的 CGM 传感器。将 NN 性能与三种替代方法（线性外推、样条外推和末次观察值结转）进行了比较。
内部验证的 RMSE 为 9.1mg/dL，MARD 为 4.2%，99.9%的预测值位于一致性误差网格的 A+B 区。外部验证的 RMSE 为 5.9-11.3mg/dL，MARD 为 3.2-5.4%，99.9-100%的预测值位于一致性误差网格的 A+B 区。与两种替代方法相比，NN 在所有参数上的性能均更优。
我们提出并验证了一种 NN 血糖预测模型，该模型可能易于使用和实施。该模型仅需要 CGM 系统的输入，即可实现 15 分钟提前期的血糖预测。该方法的内部和外部验证结果均良好。
