Accurate prediction of blood glucose variations in type 2 diabetes (T2D) will facilitate better glycemic control and decrease the occurrence of hypoglycemic episodes as well as the morbidity and mortality associated with T2D, hence increasing the quality of life of patients. Owing to the complexity of the blood glucose dynamics, it is difficult to design accurate predictive models in every circumstance, i.e., hypo/normo/hyperglycemic events. We developed deep-learning methods to predict patient-specific blood glucose during various time horizons in the immediate future using patient-specific every 30-min long glucose measurements by the continuous glucose monitoring (CGM) to predict future glucose levels in 5 min to 1 h. In general, the major challenges to address are (1) the dataset of each patient is often too small to train a patient-specific deep-learning model, and (2) the dataset is usually highly imbalanced given that hypo- and hyperglycemic episodes are usually much less common than normoglycemia. We tackle these two challenges using transfer learning and data augmentation, respectively. We systematically examined three neural network architectures, different loss functions, four transfer-learning strategies, and four data augmentation techniques, including mixup and generative models. Taken together, utilizing these methodologies we achieved over 95% prediction accuracy and 90% sensitivity for a time period within the clinically useful 1 h prediction horizon that would allow a patient to react and correct either hypoglycemia and/or hyperglycemia. We have also demonstrated that the same network architecture and transfer-learning methods perform well for the type 1 diabetes OhioT1DM public dataset.

准确预测2型糖尿病（T2D）的血糖变化将有助于更好地控制血糖，减少低血糖发作的发生以及与T2D相关的发病率和死亡率，从而提高患者的生活质量。由于血糖动态的复杂性，很难在每种情况下（即低血糖/正常/高血糖事件）设计准确的预测模型。我们开发了深度学习方法，通过连续血糖监测 (CGM) 每 30 分钟长的血糖测量来预测近期不同时间范围内患者特定的血糖，以预测 5 分钟到 1 天内的未来血糖水平h.一般来说，需要解决的主要挑战是（1）每个患者的数据集通常太小，无法训练特定于患者的深度学习模型，以及（2）考虑到低血糖和高血糖发作，数据集通常高度不平衡。通常比正常血糖少见。我们分别使用迁移学习和数据增强来应对这两个挑战。我们系统地研究了三种神经网络架构、不同的损失函数、四种迁移学习策略和四种数据增强技术，包括混合和生成模型。总而言之，利用这些方法，我们在临床有用的 1 小时预测范围内的一段时间内实现了超过 95% 的预测准确性和 90% 的灵敏度，这将使患者能够对低血糖和/或高血糖做出反应并纠正。我们还证明，相同的网络架构和迁移学习方法对于 1 型糖尿病 OhioT1DM 公共数据集表现良好。