Department of Computer Architecture, Facultad de Informática, Universidad Complutense de Madrid, 28040 Madrid, Spain.
Instituto de Tecnología del Conocimiento, Universidad Complutense de Madrid, 28040 Madrid, Spain.
Sensors (Basel). 2021 Oct 26;21(21):7090. doi: 10.3390/s21217090.
This article proposes two ensemble neural network-based models for blood glucose prediction at three different prediction horizons-30, 60, and 120 min-and compares their performance with ten recently proposed neural networks. The twelve models' performances are evaluated under the same OhioT1DM Dataset, preprocessing workflow, and tools at the three prediction horizons using the most common metrics in blood glucose prediction, and we rank the best-performing ones using three methods devised for the statistical comparison of the performance of multiple algorithms: scmamp, model confidence set, and superior predictive ability. Our analysis provides a comparison of the state-of-the-art neural networks for blood glucose prediction, estimating the model's error, highlighting those with the highest probability of being the best predictors, and providing a guide for their use in clinical practice.
本文提出了两种基于集成神经网络的模型，用于在三个不同的预测时间范围（30、60 和 120 分钟）预测血糖，并将它们的性能与最近提出的十种神经网络进行比较。在三个预测时间范围内，使用血糖预测中最常用的指标，在相同的俄亥俄州 T1DM 数据集、预处理工作流程和工具下，评估这十二个模型的性能，并使用三种方法对表现最好的模型进行排名，这三种方法是为了比较多种算法的性能而设计的：scmamp、模型置信集和优越预测能力。我们的分析比较了血糖预测的最新神经网络，估计了模型的误差，突出了那些最有可能成为最佳预测器的模型，并为它们在临床实践中的应用提供了指导。
