RESUMEN
Background: Glycosylated hemoglobin (HbA1c) is recommended for diagnosing and monitoring type 2 diabetes. However, the monitoring frequency in real-world applications has not yet reached the recommended frequency in the guidelines. Developing machine learning models to screen patients with poor glycemic control in patients with T2D could optimize management and decrease medical service costs. Methods: This study was carried out on patients with T2D who were examined for HbA1c at the Sichuan Provincial People's Hospital from April 2018 to December 2019. Characteristics were extracted from interviews and electronic medical records. The data (excluded FBG or included FBG) were randomly divided into a training dataset and a test dataset with a radio of 8:2 after data pre-processing. Four imputing methods, four screening methods, and six machine learning algorithms were used to optimize data and develop models. Models were compared on the basis of predictive performance metrics, especially on the model benefit (MB, a confusion matrix combined with economic burden associated with therapeutic inertia). The contributions of features were interpreted using SHapley Additive exPlanation (SHAP). Finally, we validated the sample size on the best model. Results: The study included 980 patients with T2D, of whom 513 (52.3%) were defined as positive (need to perform the HbA1c test). The results indicated that the model trained in the data (included FBG) presented better forecast performance than the models that excluded the FBG value. The best model used modified random forest as the imputation method, ElasticNet as the feature screening method, and the LightGBM algorithms and had the best performance. The MB, AUC, and AUPRC of the best model, among a total of 192 trained models, were 43475.750 (¥), 0.972, 0.944, and 0.974, respectively. The FBG values, previous HbA1c values, having a rational and reasonable diet, health status scores, type of manufacturers of metformin, interval of measurement, EQ-5D scores, occupational status, and age were the most significant contributors to the prediction model. Conclusion: We found that MB could be an indicator to evaluate the model prediction performance. The proposed model performed well in identifying patients with T2D who need to undergo the HbA1c test and could help improve individualized T2D management.
RESUMEN
Objective: Acute lung injury (ALI) is one of the common and severe complications of cardiopulmonary bypass (CPB), which is the primary cause of death in intensive care units. Nevertheless, there is a lack of effective treatment for ALI secondary to CPB. κ-Opioid receptor (KOR) agonists have been demonstrated to improve lung function after pulmonary hypertension. However, its protective role has been barely reported in CPB-induced acute respiratory distress syndrome (ARDS). Therefore, this research focused on the protective effect of a KOR agonist U50448H on ARDS and investigated its potential relationship with the NOD-like receptor family pyrin domain-containing 3 (NLRP3) inflammasome. Method: Forty-five rats were randomly allocated into Sham, CPB, and U50448 groups (n = 15 rats/group). After a CPB model was successfully established in rats, CPB rats were treated with the KOR agonist U50448H. The values of extravascular lung water (EVLW), alveolar-arterial oxygen tension difference (AaDO2), and respiratory index (RI) were examined, and the lung wet/dry (W/D) weight ratio was also calculated. Western blot (WB) was utilized to measure the expression of MMP-9, GSDMD-C, GSDMD-N, NLRP3, ASC, pro-Caspase-1, pro-IL-1ß, and α7-nAChR. The immunofluorescence assay was performed for examining the expression of ROS, F480, iNOS, CD206, and α7-nAChR. Cell apoptosis was detected by the TUNEL assay. ELISA was used to test the level of LPS in serum and the level of MDA, GSH, SOD, TNF-α, IL-4, IL-6, IL-18, and IL-1ß in lung tissues. Results: It was observed that the administration of U50448H significantly reduced EVLW values and LPS levels in the lung of rats. Meanwhile, U50448H increased AaDO2 values while decreasing RI values. Moreover, the administration of U50448H alleviated the pathological damage caused by ALI secondary to CPB. U50448H repressed ROS release and oxidative stress responses, as well as lowered LPS levels in plasma and MMP-9 expression in the lung of CPB rats. Furthermore, U50448H facilitated the shift of macrophage phenotype to M2. In addition, U50448H decreased the activity of the CAP-NLRP3 inflammasome and suppressed pyroptosis in pulmonary cells. Conclusion: The KOR agonist U50448H improved lung function and relieved lung injury in CPB rats, accompanied by diminished ROS and MMP-9 levels in lung tissues, promoted macrophage polarization from M1 to M2, and reduced NLRP3 inflammasome activities. These results indicated U50448H as a promising drug for the treatment of ALI secondary to CPB.
RESUMEN
OBJECTIVE: To observe the effects of dexmedetomidine (DEX) on glutamate (Glu), aspartic acid (Asp) release and NMDAR1 expression in hippocampus in global cerebral ischemia/reperfusion rats, and investigate the protective effect and the related mechanism of neurotransmitters. METHODS: Fifty-four male Wistar rats were randomly divided into three groups (n=18):sham group(A), ischemia/reperfusion group(B), dexmedetomidine pretreatment group(C). Total cerebral ischemia model was set up by four vessel occlusion in rats. Glu and Asp levels were measured with microdialysis at different time. Then the animals were decapitated and the brains were immediately removed to detect NMDAR1 expression in hippocampus area by immunohistochemistry and Western-blot. RESULTS: Compared with that in group B, the levels of Glu, Asp and NMDA NR1 protein were significantly decreased in the dexmedetomidine pretreatment group (P<0.05 or 0.01). CONCLUSIONS: Dexmedetomidine might has a protective effect on hippocampus in global cerebral ischemia/reperfusion animals. The protective mechanism might be involved in inhibiting excitatory amino acids(EAA) release and NMDAR1 expression.