1.Meteorological factor-driven prediction of high-use days of budesonide: construction and comparison of ensemble learning models
Qitao CHEN ; Yue ZHOU ; Xiaojun ZHANG ; Jingwen NI ; Guoqiang SUN ; Fenfei GAO ; Lizhen XIA ; Zihao LI
China Pharmacy 2025;36(21):2723-2726
OBJECTIVE To construct ensemble learning models for predicting high-use days of budesonide based on meteorological factors, thereby providing reference for hospital pharmacy management. METHODS Meteorological data for 2024 and outpatient budesonide usage data from the jurisdiction of Sanming Hospital of Integrated Traditional Chinese and Western Medicine were collected. High-use days were defined as the 75th percentile of outpatient budesonide usage, and a corresponding dataset was established. The prediction task was formulated as a classification problem, and three ensemble learning models were developed: Random Forest, Extreme Gradient Boosting (XGBoost), and Histogram-based Gradient Boosting Classifier. Model performance was evaluated using accuracy, precision, recall, F1-score, and log-loss. Model interpretability was analyzed using Shapley Additive Explanations (SHAP). RESULTS The Histogram-based Gradient Boosting Classifier achieved the best performance (accuracy=0.75, F1-score=0.48), followed by XGBoost (accuracy=0.74, F1-score=0.43) and Random Forest (accuracy=0.72, F1-score=0.22). SHAP results suggested that the prediction results of the last two models have the highest correction. CONCLUSIONS Ensemble learning models can effectively predict high-use days of budesonide, with the Histogram- based Gradient Boosting Classifier demonstrating the best predictive performance. Low temperature, high humidity, and low atmospheric pressure show significant positive impacts on the prediction of daily budesonide usage.
2.An experimental study of quercetin attenuating neuroinflammation in epileptic rats through HMGB1/RAGE/NF-κB pathway
Qiongying WU ; Wenyong GAO ; Yanping AI ; Haitang WEI ; Fenfei WEI
Chinese Journal of Immunology 2024;40(8):1601-1606
Objective:To investigate whether quercetin reduces neuroinflammation in epileptic rats by regulating high mobility group protein B1(HMGB1),receptor for advanced glycation end products(RAGE)and nuclear factor kappa-B(NF-κB),and to explore the possibility of HMGB1/RAGE/NF-κB pathway as a new target of quercetin.Methods:Twelve SD rats were randomly selected from 60 SD rats as healthy group,and the remaining rats were used to construct experimental models of epilepsy rats.Rats that were successfully modeled were divided into model group,high-dose quercetin group,low-dose quercetin group,quercetin+pathway activator group,with 12 rats in each group.Pathological changes of hippocampal tissue of rats were observed;neurobehavioral function of rats was evaluated;levels of tumor necrosis factor-α(TNF-α),IL-6 and IL-1β,and mRNA and protein expression levels of HMGB1,RAGE,NF-κB in hippocampal tissue of rats were detected.Results:Structure of hippocampus of rats in healthy group was complete;compared with healthy group,structure of hippocampal tissue of rats in model group was scattered,the number of surviving neurons was observably reduced,apoptotic index was observably increased,the Racine grade was observably increased,TNF-α,IL-1β,IL-6 contents and mRNA and protein expression levels of HMGB1,RAGE,NF-κB in hippocampal tissue were significantly increased;com-pared with model group,structure of hippocampal tissue of rats in low-and high-dose quercetin groups was relatively complete,the number of surviving neurons was observably increased,apoptotic index was observably decreased,the Racine grade was significantly decreased,TNF-α,IL-1β,IL-6 contents and mRNA and protein expression levels of HMGB1,RAGE,NF-κB were significantly re-duced,and the improvement effect of high-dose quercetin group was better;compared with high-dose quercetin group,the number of surviving neurons in quercetin+pathway activator group was significantly reduced,apoptotic index was significantly increased,the Ra-cine grade was significantly increased,TNF-α,IL-1β,IL-6 contents and mRNA and protein expression levels of HMGB1,RAGE,NF-κB in hippocampal tissue were significantly increased.Conclusion:Quercetin can effectively reduce neuroinflammation in epilep-tic rats by inhibiting the HMGB1/RAGE/NF-κB pathway and reducing the mRNA and protein expressions of related genes.
3.Effect of quaternary ammonium salt derivative of haloperidol on L-type currents in rat ventricular myocytes
Zhanqin HUANG ; Ganggang SHI ; Jinhong ZHENG ; Fenfei GAO ; Xingping LIU ;
Chinese Pharmacological Bulletin 2003;0(10):-
AIM To study the effect of quaternary ammonium salt derivative of haloperidol (F 2) on L type calcium current ( I Ca ) in rat ventricular myocytes. METHODS Single ventricular cell of rat was obtained by enzymatic dissociation method. The currents were recorded with the whole cell configuration of the patch clamp technique. RESULTS F 2(1 ?mol?L -1 ) decreased I Ca from ( 1 775 2 ?360 4) pA to (464?129 1) pA ( n =8, P

Result Analysis
Print
Save
E-mail