Comprehensive assessment of ocular parameters for identifying diagnostic indicators of diabetic peripheral neuropathy.

PURPOSE: To explore variations in systemic and ocular parameters among patients with diabetes, both with and without diabetic peripheral neuropathy (DPN) and to identify sensitive indicators for DPN diagnosis. METHODS: Ninty-five patients with type 2 diabetes mellitus (T2DM) were involved in this cross-sectional study, including 49 without DPN and 46 with DPN. Ocular parameters were obtained using optical coherence tomography angiography (OCTA) and corneal confocal microscopy (CCM). RESULT: Patients with DPN presented with significantly higher HbA1c (p < 0.05) and glycated albumin (GA, p < 0.01) levels, increased prevalence of diabetic retinopathy (DR, p < 0.05), and lower serum albumin (ALB, p < 0.01) and red blood cell (RBC, p < 0.05) levels. Ocular assessments revealed reduced corneal nerve fiber length (CNFL, p < 0.001) and enlarged foveal avascular zone (FAZ) area (p < 0.05) in DPN group. Logistic regression analysis indicated a significant association of presence of DR, RBC, GA, ALB, CNFL and DPN (p < 0.05, respectively). In the binary logistic regression for DPN risk, all three models including the presence of DR and CNFL exhibited the area under the curve (AUC) exceeding 0.8. CONCLUSION: The study establishes a strong correlation between ocular parameters and DPN, highlighting CCM's role in early diagnosis. Combining systemic and ocular indicators improves DPN risk assessment and early management.

Federated Learning-Based Insulator Fault Detection for Data Privacy Preserving.

Insulators are widely used in distribution network transmission lines and serve as critical components of the distribution network. The detection of insulator faults is essential to ensure the safe and stable operation of the distribution network. Traditional insulator detection methods often rely on manual identification, which is time-consuming, labor-intensive, and inaccurate. The use of vision sensors for object detection is an efficient and accurate detection method that requires minimal human intervention. Currently, there is a considerable amount of research on the application of vision sensors for insulator fault recognition in object detection. However, centralized object detection requires uploading data collected from various substations through vision sensors to a computing center, which may raise data privacy concerns and increase uncertainty and operational risks in the distribution network. Therefore, this paper proposes a privacy-preserving insulator detection method based on federated learning. An insulator fault detection dataset is constructed, and Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) models are trained within the federated learning framework for insulator fault detection. Most of the existing insulator anomaly detection methods use a centralized model training method, which has the advantage of achieving a target detection accuracy of over 90%, but the disadvantage is that the training process is prone to privacy leakage and lacks privacy protection capability. Compared with the existing insulator target detection methods, the proposed method can also achieve an insulator anomaly detection accuracy of more than 90% and provide effective privacy protection. Through experiments, we demonstrate the applicability of the federated learning framework for insulator fault detection and its ability to protect data privacy while ensuring test accuracy.

Thiamin and riboflavin status with related enzyme activities in pulmonary tuberculosis with diabetes mellitus in Shandong province of China.

BACKGROUND AND OBJECTIVES: Poor nutritional status is a common finding in pulmonary tuberculosis (TB) patients with and without type 2 diabetes mellitus (T2DM), thiamin (VB-1) and riboflavin (VB-2) are coenzymes important for the activation of many enzymes involved in improving nutritional status. We aimed to investigate enzymatic activities and the associations between VB-1 and VB-2, and their relations to nutritional status in TB and TB+T2DM patients. METHODS AND STUDY DESIGN: This was a cross-sectional study that prospectively enrolled TB 40 patients with or without T2DM respectively from the Chest Hospital of Qingdao and 76 healthy controls with similar age and gender distributions were recruited from the medical center of the affiliated hospital of Qingdao Medical College. The erythrocyte transketolase activation coefficient (ETKac, for VB-1 deficiency), the glutathione reductase activation coefficient (EGRac, for VB-2 deficiency), and metabolic enzyme activities were analyzed. RESULTS: VB-1 and VB-2 deficiency rates were higher, and enzyme activities were lower in TB and TB+T2DM relative to control group. ETKac and EGRac were negatively correlated with enzyme activities, either with body mass index (BMI), while enzyme activities were positively associated with BMI. CONCLUSIONS: VB-1 and VB-2 concentrations were lower in TB patients with or without T2DM relative to controls, with concomitant reductions in the activity levels of key metabolic enzymes. Significant correlations were observed between VB-1 and VB-2 concentrations and the activity of these metabolic enzymes, they all correlated with nutrition status. VB-1 and VB-2 concentrations may thus impact metabolic enzyme activity and thereby influence nutritional status.