Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background: and Purpose Symptomatic intracranial hemorrhage (sICH) following endovascular thrombectomy (EVT) is a severe complication associated with adverse functional outcomes and increased mortality rates. Currently, a reliable predictive model for sICH risk after EVT is lacking. Methods: This study used data from patients aged ≥20 years who underwent EVT for anterior circulation stroke from the nationwide Taiwan Registry of Endovascular Thrombectomy for Acute Ischemic Stroke (TREAT-AIS). A predictive model including factors associated with an increased risk of sICH after EVT was developed to differentiate between patients with and without sICH. This model was compared existing predictive models using nationwide registry data to evaluate its relative performance. Results: Of the 2,507 identified patients, 158 developed sICH after EVT. Factors such as diastolic blood pressure, Alberta Stroke Program Early CT Score, platelet count, glucose level, collateral score, and successful reperfusion were associated with the risk of sICH after EVT. The TREAT-AIS score demonstrated acceptable predictive accuracy (area under the curve [AUC]=0.694), with higher scores being associated with an increased risk of sICH (odds ratio=2.01 per score increase, 95% confidence interval=1.64–2.45, P<0.001). The discriminatory capacity of the score was similar in patients with symptom onset beyond 6 hours (AUC=0.705). Compared to existing models, the TREAT-AIS score consistently exhibited superior predictive accuracy, although this difference was marginal. Conclusions The TREAT-AIS score outperformed existing models, and demonstrated an acceptable discriminatory capacity for distinguishing patients according to sICH risk levels. However, the differences between models were only marginal. Further research incorporating periprocedural and postprocedural factors is required to improve the predictive accuracy.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: To investigate the potential protective effect of Shexiang Tongxin dropping pills (STDP) on ischemia-reperfusion injury and its underlying mechanisms in improving endothelial cell function in coronary microvascular disease (CMVD). Methods: A rat model of myocardial ischemia-reperfusion injury with CMVD was established using ligation and reperfusion of the left anterior descending artery. The effect of STDP (21.6 mg/kg) on cardiac function was evaluated using echocardiography, hematoxylin-eosin staining, and Evans blue staining. The effects of STDP on the microvascular endothelial barrier were assessed based on nitric oxide production, endothelial nitric oxide synthase expression, structural variety of tight junctions (TJs), and the expression of zonula occludens-1 (ZO-1), claudin-5, occludin, and vascular endothelial (VE)-cadherin proteins. The mechanisms of STDP (50 and 100 ng/mL) were evaluated by examining the expression of sphingosine 1-phosphate receptor 2 (S1PR2), Ras Homolog family member A (RhoA), and Rho-associated coiled-coil-containing protein kinase (ROCK) proteins and the distribution of ZO-1, VE-cadherin, and F-actin proteins in an oxygen and glucose deprivation/reoxygenation model. Results: The administration of STDP on CMVD rat model significantly improved cardiac and microvascular endothelial cell barrier functions (all P < .05). STDP enhanced the structural integrity of coronary microvascular positioning and distribution by clarifying and completing TJs and increasing the expression of ZO-1, occludin, claudin-5, and VE-cadherin in vivo (all P < .05). The S1PR2/RhoA/ROCK pathway was inhibited by STDP in vitro, leading to the regulation of endothelial cell TJs, adhesion junctions, and cytoskeletal morphology. Conclusion STDP showed protective effects on cardiac impairment and microvascular endothelial barrier injury in CMVD model rats induced by myocardial ischemia-reperfusion injury through the modulation of the S1PR2/RhoA/ROCK pathway.

BACKGROUND: G protein-coupled receptor kinase 2 (GRK2) could participate in the regulation of diverse cells via interacting with non-G-protein-coupled receptors. In the present work, we explored how paroxetine, a GRK2 inhibitor, modulates the differentiation and activation of immune cells in rheumatoid arthritis (RA). METHODS: The blood samples of healthy individuals and RA patients were collected between July 2021 and March 2022 from the First Affiliated Hospital of Anhui Medical University. C57BL/6 mice were used to induce the collagen-induced arthritis (CIA) model. Flow cytometry analysis was used to characterize the differentiation and function of dendritic cells (DCs)/T cells. Co-immunoprecipitation was used to explore the specific molecular mechanism. RESULTS: In patients with RA, high expression of GRK2 in peripheral blood lymphocytes, accompanied by the increases of phosphatidylinositol 3 kinase (PI3K), protein kinase B (AKT), and mammalian target of rapamycin (mTOR). In animal model, a decrease in regulatory T cells (T regs ), an increase in the cluster of differentiation 8 positive (CD8 + ) T cells, and maturation of DCs were observed. Paroxetine, when used in vitro and in CIA mice, restrained the maturation of DCs and the differentiation of CD8 + T cells, and induced the proportion of T regs . Paroxetine inhibited the secretion of pro-inflammatory cytokines, the expression of C-C motif chemokine receptor 7 in DCs and T cells. Simultaneously, paroxetine upregulated the expression of programmed death ligand 1, and anti-inflammatory cytokines. Additionally, paroxetine inhibited the PI3K-AKT-mTOR metabolic pathway in both DCs and T cells. This was associated with a reduction in mitochondrial membrane potential and changes in the utilization of glucose and lipids, particularly in DCs. Paroxetine reversed PI3K-AKT pathway activation induced by 740 Y-P (a PI3K agonist) through inhibiting the interaction between GRK2 and PI3K in DCs and T cells. CONCLUSION Paroxetine exerts an immunosuppressive effect by targeting GRK2, which subsequently inhibits the metabolism-related PI3K-AKT-mTOR pathway of DCs and T cells in RA.
G-Protein-Coupled Receptor Kinase 2/metabolism* ; Arthritis, Rheumatoid/immunology* ; Animals ; Dendritic Cells/metabolism* ; Paroxetine/therapeutic use* ; Proto-Oncogene Proteins c-akt/metabolism* ; Mice ; Humans ; Mice, Inbred C57BL ; Signal Transduction/drug effects* ; Male ; Phosphatidylinositol 3-Kinases/metabolism* ; Lymphocyte Activation/drug effects* ; Female ; T-Lymphocytes/metabolism* ; Middle Aged