Objective: Insulin-induced hypoglycemia is recognized as a critical problem for diabetic patients, especially at night. To give glucose predictions and advance warnings of hypoglycemia of at least 30 minutes, various glucose-insulin models have been proposed. Recognizing the complementary nature of the models, this research proposes a Glucose-Insulin Mixture (GIM) model to predict the glucose values for hypoglycemia detection, by optimally fusing different models with its adjusted parameters to address the inter- and intra-individual variability. Methods: Two types of classic glucose-insulin models, the Ruan model, with single-compartment glucose kinetics, and the Hovorka model, with two-compartment glucose kinetics, are selected as two candidate models. Based on Bayesian inference, GIM is introduced with quantified contributions from the models with the associated parameters. GIM is then applied to predict the glucose values and hypoglycemia events. Results: The proposed model is validated by the nocturnal glucose data collected from 12 participants with type 1 diabetes. The GIM model has promising fitting of RMSE within 0.3465 mmol/L and predicting of RMSE within 0.5571 mmol/L. According to the literature, the hypoglycemia is defined as 3.9 mmol/L, and the GIM model shows good short-term hypoglycemia prediction performance with the data collected within the last hour (accuracy: 95.97%, precision: 91.77%, recall: 95.60%). In addition, the probability of hypoglycemia event in 30 minutes is inferred. Conclusion: GIM, by fusing various glucose-insulin models via Bayesian inference, has the promise to capture glucose dynamics and predict hypoglycemia. Significance: GIM based short-term hypoglycemia prediction has potential clinical utility for timely intervention.

Fault diagnosis transfer learning models commonly employ deep neural networks (DNNs) to analyze time–frequency features. However, excessively DNNs can result in diminished generalization capabilities, leading to subpar performance of the model across various working conditions. Furthermore, inappropriate domain adaptation (DA) strategies significantly constrain the accuracy of the model. To address this issue, a robustly optimized residual-network and vision transformer (ViT) domain adaptation model is proposed in this article, combining wavelet packet transform (WPT), residual networks, and self-attention mechanisms. Firstly, the WPT is utilized to construct multi-band wavelet coefficient matrix (MWCM) and corresponding multi-band wavelet coefficient time–frequency feature matrix (MWSM) with small size and feature aggregation. Subsequently, a shallow robustly optimized residual network is designed to effectively extract features from MWCM, considering the spatial distance dependencies of features. Additionally, ViT is employed for time–frequency global feature extraction from MWSM. Furthermore, domain adversarial neural network and multi-kernel maximum mean discrepancy are employed to extract domain-invariant features from signals of different operating conditions and fault types. At last, three fault diagnosis experiments are conducted in multi-condition scenarios of bearings. The experimental results illustrate the superiority and effectiveness of the proposed model.

Accurate glucose prediction plays an important role in glucose management and closed-loop insulin delivery for subjects with diabetes. Due to its powerful data mining capability, neural networks are used to grasp the glucose trends from continuous glucose monitoring (CGM) data. However, this approach requires a large number of individual data and plentiful computing resources, but has relatively poor interpretability. Given that the glucose metabolism mechanism model contains abundant physiological information, fusing the information with neural networks can reduce the demand for data and computing resources, and improve interpretability. In this study, a physics-informed glucose-insulin neural network (PIGNN) model is proposed, of which the structure and loss function are designed based on the glucose-insulin dynamic model. According to the experiments of 22 real subjects and 30 in-silico subjects with type 1 diabetes, the prediction accuracy of this method achieves 0.726 ± 0.126 mmol/L. Compared with models without physical information, the proposed PIGNN shows a significant improvement in glucose prediction for real subjects with a limited sample size (only 48 data samples), resulting in an accuracy improvement of 12.33%. In addition, it is proved that with limited data more physical information can improve the glucose prediction accuracy significantly.

The insulin pump is a critical device for intensive insulin therapy in diabetic patients. Failures in insulin pump sets such as blockage and leakage can disrupt normal insulin delivery, potentially causing hyperglycemia or life-threatening diabetic ketoacidosis. Developing a mathematical model to accurately describe the failure mechanisms of insulin pump sets is essential for fault diagnosis and performance optimization. However, modeling these systems is challenging due to the interplay of rigid and elastic constraints (e.g., needles and hoses) and multi-domain interactions (e.g., fluid insulin and solid components). To address these challenges, this study establishes a mathematical model for insulin pump sets with blockage and leakage faults based on the power flow method. The model is used to investigate the effects of these faults on insulin fluid dynamics, with a focus on impacts of failures at various positions. Numerical results demonstrate a maximum error of 0.57% compared to simulation data. Findings reveal that leakage faults closer to the flow source significantly reduce the output flow rate and chamber pressure. Conversely, as blockage approach the flow source, the impact on reducing flow rate diminishes, while their influence on increasing chamber pressure becomes more pronounced. Notably, when the blockage thickness exceeds 0.6 mm, both flow rate and pressure are markedly affected, with the effects intensifying as the thickness increases.