Glucose–insulin models, testing glucose sensors and support systems for health care decisions play an important role in synthesis of glucose control algorithms. In this work we propose an online glucose–insulin identification using the Recurrent High Order Neural Network (RHONN). Then, the model obtained is used to predict $n$-steps forward of glucose levels, also by RHONN. The used data for identification is from a Type 1 Diabetes Mellitus (T1DM) patient, it was collected from the Continuous Monitoring Glucose System (CMGS) by MiniMed Inc ® and an insulin pump by Paradigm Real-time Insulin Pump ®. RHONN is trained online by Extended Kalman Filter (EKF). The results suggest that it is possible to make a prediction of up to 35 min in the future, which it would help to prevent risky events (hypoglycemia and hyperglycemia). Also shows that, it could be directly connected to a CGMS to help the patient improve the glucose control and even an automatic glucose control algorithm. The proposed Neural Network shows good performance compared to baseline methods in terms of evaluation criteria.

葡萄糖-胰岛素模型、测试葡萄糖传感器和医疗保健决策支持系统在合成葡萄糖控制算法中发挥着重要作用。在这项工作中，我们建议使用循环高阶神经网络 (RHONN) 进行在线葡萄糖 - 胰岛素识别。然后，将得到的模型用于预测$n$- 提高葡萄糖水平，也是 RHONN。用于识别的数据来自 1 型糖尿病 (T1DM) 患者，它是从 MiniMed Inc ® 的连续监测葡萄糖系统 (CMGS) 和 Paradigm 实时胰岛素泵 ® 的胰岛素泵中收集的。RHONN 由扩展卡尔曼滤波器 (EKF) 在线培训。结果表明，未来有可能做出长达 35 分钟的预测，这将有助于预防风险事件（低血糖和高血糖）。还表明，它可以直接连接到CGMS，帮助患者改善血糖控制甚至自动血糖控制算法。与基线方法相比，所提出的神经网络在评估标准方面表现出良好的性能。