Department of Health Science and Technology, Aalborg University, Denmark.
Department of Health Science and Technology, Aalborg University, Denmark.
Comput Biol Med. 2021 Nov;138:104865. doi: 10.1016/j.compbiomed.2021.104865. Epub 2021 Sep 15.
Numerous attempts to predict glucose value from continuous glucose monitors (CGM) have been published. However, there is a lack of proper analysis and modeling of penalty for errors in different glycemic ranges. The aim of this study was to investigate the potential for developing glucose prediction models with focus on the clinical aspects.
We developed and compared six different models to test which approach were best suited for predicting glucose levels at different lead times between 10 and 60 min. The models were: last observation carried forward, linear extrapolation, ensemble methods using LSBoost and bagging, neural networks, one without error-weights and one with error-weights. The modeling and test were based on 225 type 1 diabetes patients with 315,000 h of CGM data.
Results show that it is possible to predict glucose levels based on CGM with a reasonable accuracy and precision with a 30-min prediction lead time. A comparison of different methods shows that there are improvements on performance gained from using more advanced machine learning algorithms (MARD 10.26-10.79 @ 30-min lead time) compared to a simple modeling (MARD 10.75-12.97 @ 30-min lead time). Moreover, the proposed use of error weights could lead to better clinical performance of these models, which is an important factor for real usage. E.g., the percentages in the C-zone of the consensus error grid without error-weights (0.57-0.68%) vs including error-weights (0.28%).
The results point toward that using error weighting in the training of the models could lead to better clinical performance.
已经有许多尝试通过连续血糖监测仪（CGM）来预测血糖值的报道。然而，在不同血糖范围内，对于错误的惩罚缺乏适当的分析和建模。本研究的目的是研究开发专注于临床方面的血糖预测模型的潜力。
我们开发并比较了六种不同的模型，以测试在 10 到 60 分钟的不同前置时间内，哪种方法最适合预测血糖水平。这些模型包括：末次观察值结转、线性外推、使用 LSBoost 和套袋的集成方法、神经网络、没有误差权重的模型和具有误差权重的模型。建模和测试基于 225 名 1 型糖尿病患者的 315000 小时 CGM 数据。
结果表明，基于 CGM 以合理的精度和精密度预测血糖水平是可行的，预测前置时间为 30 分钟。不同方法的比较表明，与简单建模相比（MARD 10.75-12.97 @ 30 分钟前置时间），使用更先进的机器学习算法（MARD 10.26-10.79 @ 30 分钟前置时间）可以提高性能。此外，建议使用误差权重可以提高这些模型的临床性能，这是实际使用的重要因素。例如，共识误差网格中无误差权重（0.57-0.68%）和包含误差权重（0.28%）的 C 区的百分比。
结果表明，在模型训练中使用误差加权可以提高临床性能。
