Esophageal cancer （EC） is a highly prevalent malignant tumor in China. The phosphatidylinositol 3-kinase （PI3K）/protein kinase B （Akt） signaling pathway， as one of the key oncogenic pathways， can promote the cell cycle progression， proliferation， migration， and invasion， induce chemoresistance， and inhibit apoptosis and autophagy of EC cells. Traditional Chinese medicine （TCM）， with the advantages of targeting multiple points with multiple components to delay cancer progression， can target the PI3K/Akt signaling pathway for EC treatment. This article preliminarily discusses the molecular mechanism and role of the PI3K/Akt signaling pathway in EC and elaborates on the specific targets and efficacy of TCM in treating EC through intervention in the PI3K/Akt signaling pathway in the past five years. TCM materials and extracts inhibiting the PI3K/Akt signaling pathway in EC include Borneolum， spore powder of Ganoderma lucidum without spore coat， extract of Celastrus orbiculatus， root extract of Taraxacum， and Bruceae Fructus oil emulsion. TCM active ingredients exerting the effect include flavonoids， terpenoids， saponins， phenols， polysaccharides， alkaloids， and other compounds. TCM compound prescriptions with such effect include Qige San， Huqi San， Xuanfu Daizhetang， Tongyoutang and its decomposed prescriptions， Liujunzi Tang， and Xishenzhi Formula. In addition， TCM injections such as Compound Kushen Injection and Kang'ai injection also inhibit the PI3K/Akt signaling pathway in EC. This paper summarizes the role of the PI3K/Akt signaling pathway in EC and the TCM interventions， aiming to provide reference for the research and clinical application of new drugs for EC.

Objective To investigate the key factors influencing the willingness of chronic disease patients to participate in home pharmaceutical services.Methods The study adopted the data from inner Mongolia and northeast China set of the drug aging system research for China.The Null Importance method was employed to identify key factors influencing the willingness of chronic disease patients to participate in home pharmaceutical services.The logistic regression model was constructed and evaluated the impact of feature selection through 5 fold cross-validation and accuracy and AUC values.Results 10 key factors were selected by the Null Importance method and the performance of the logistic regression model was improved after feature selection.The factors which significantly affected patients' willingness to accept home pharmaceutical services included the number of accessible information sources(OR=1.261,95％CI=1.182～1.345),medication therapeutic indication cognition(OR=1.342,95％CI=1.124～1.603),the presence the drug packaging or not(OR=1.218,95％CI=1.015～1.462),medication adherence(OR=0.881,95％CI=0.839～0.925),medication literacy(OR=0.631,95％CI=0.488～0.817),the degree of know of medication guidance services(OR=1.211,95％CI=1.017～1.442).Conclusion The logistic model refined by the Null Importance feature selection method demonstrated good performance and was conducive to analyzing the factors influencing the willingness of chronic disease patients to participate in home pharmaceutical care.

Objective To evaluate the efficacy,safety and cost-effectiveness of dorzagliatin in the treatment of type 2 diabetes mellitus using a rapid health technology assessment,and to provide medical evidence for clinical decision-making.Methods PubMed,Embase,Cochrane Library,CNKI,Wanfang Data,SinoMed and relevant health technology assessment(HTA)websites and databases were searched to collect systematic reviews/Meta-analysis,pharmacoeconomic literature and HTA reports of dorzagliatin in the treatment of type 2 diabetes from inception to July 20,2024.Two reviewers independently screened literature,extracted date and assessed quality.The results were qualitatively described and analyzed.Results A total of 6 studies were included,including 5 systematic reviews/Meta-analysis and a pharmacoeconomic study.In terms of efficacy compared with placebo,dorzagliatin significantly reduced glycated hemoglobin(HbA1c),fasting plasma glucose,2-hour postprandial blood glucose and insulin resistance index(P＜0.05),improved HbA1c compliance rate in terms of safety,dorzagliatin,and enhanced homeostasis model assessment-β(P＜0.05),significantly increased total cholesterol,triglyceride,body weight and body mass index(P＜0.05).In terms of safety,the total incidence of adverse reactions of dorzagliatin was slightly higher than that of the placebo group(P＜0.05).However,there was no significant difference in the incidence of severe adverse reactions between the two groups(P＞0.05),and there was no significant increase in the incidence of hyperlipidemia and hypoglycemia(P＞0.05).In terms of economy,the treatment of dorzagliatin combined with metformin has a long-term cost-utility advantage,with an economic probability of nearly 70％.Conclusion Compared with placebo,dorzagliatin has a good overall efficacy and safety in the treatment of type 2 diabetes.In terms of safety,the total incidence of adverse reactions of dorzagliatin was slightly higher than that of placebo.In terms of economy,compared with metformin alone,dorzagliatin combined with metformin has economic advantages.However,there is a lack of head-to-head comparisons of doxorubicin with other classes of glucose-lowering medications,and none of the included studies described long-term cardiac,cerebral,or renal benefits,which limits the comprehensive evaluation of the efficacy and safety of dorzagliatin.

Objective Based on the propensity score matching(PSM),the effect of flexible ureteroscopy combined with flexible negative pressure suction sheath in the treatment of infectious renal calculus lithotomy was analyzed.Methods From April 2022 to April 2024,87 patients with infectious renal calculus in our hospital were selected retrospectively.All patients were treated with flexible ureteroscopic lithotripsy(FURL).According to the different choice of ureteral access sheath(UAS)during operation,they were divided into negative pressure sheath group(n=43)and conventional sheath group(n=44).In the negative pressure sheath group,the flexible negative pressure suction sheath was used for FURL,and in the conventional sheath group,the conventional sheath was used for FURL.The general data of patients with infectious renal calculus between groups were compared,and the indicators were balanced by PSM.The clinical efficacy,perioperative indicators,levels of procalcitonin(PCT)and white blood cell count(WBC)and postoperative complications of patients with infectious renal calculus were compared between the two groups.Results After 1∶1 ratio matching by PSM,42 pairs of patients with infectious renal calculus were obtained,.The stone clearance rate of negative pressure sheath group[90.48%(38/42)]was significantly higher than that of conventional sheath group[71.43%(30/42)](P<0.05).The minimum intrapelvic pressure,average intrapelvic pressure and maximum intrapelvic pressure in the negative pressure sheath group were lower than those in the conventional sheath group,operation time and hospitalization time in the negative pressure sheath group were shorter than those in the conventional sheath group(P<0.05).The levels of PCT and WBC in the negative pressure sheath group were lower than those in the conventional sheath group at 2 h after operation,and the time for PCT and WBC to recover to the normal level were shorter than those in the conventional sheath group(P<0.05).The total incidence of postoperative complications in negative pressure sheath group[9.52%(4/42)]was significantly lower than that in conventional sheath group[28.57%(12/42)](P<0.05).Conclusion Flexible ureteroscopy combined with flexible negative pressure suction sheath is effective in the treatment of renal calculus,which is helpful to reduce intra-operative renal pelvis pressure,shorten operation time,reduce PCT and WBC levels after operation,and promote patients'early recovery with good safety.

Objective To explore the risk factors for vancomycin-related acute kidney injury(VA-AKI)in elderly patients.Methods Clinical data of elderly inpatients who used vancomycin at the Inner Mongolia Autonomous Region People's Hospital from January 2021 to June 2024 were retrospectively collected.The incidence of VA-AKI and the situation of treatment drug monitoring(TDM)were statistically analyzed.LASSO regression was used for feature selection,and this process was repeated 10,000 times.In each iteration,75％of the training samples were randomly selected,and the frequency of each feature being selected was counted.Finally,the features with higher frequency in multiple iterations were selected for model training.The data were divided into training set and test set at an 8∶2 ratio.Four machine learning prediction models,including Logistic regression,random forest,extreme gradient boosting(XGBoost),and support vector machine(SVM),were established.The accuracy and area under the receiver operating characteristic curve(AUC)of the above prediction models were calculated in the test set.The minimum depth distribution was used to visualize the importance of the characteristics of the model.Results A total of 305 elderly patients receiving vancomycin were included,among which 49 cases(16.07％)developed VA-AKI.LASSO regression analysis selected 7 characteristic variables to build 4 machine learning models,and finally selected the random forest model as the risk prediction model.The random forest model has an AUC value of 0.91,an accuracy of 0.89,an accuracy of 0.88,a recall rate of 0.98,and an F1 value of 0.93.The predictor importance ranking was in order of post-treatment creatinine level,C-reactive protein(CRP),albumin(Alb),respiratory failure,cardiac insufficiency,trough concentration time,and dose.Conclusion Post-treatment creatinine level,respiratory weakness,trough concentration time,cardiac insufficiency,Alb,CRP,and dosage were the risk factors for VA-AKI.The random forest model is the most effective in predicting the risk of VA-AKI in elderly patients,providing a reference for rational use of vancomycin in elderly patients.

Objective To explore the risk factors for vancomycin-related acute kidney injury(VA-AKI)in elderly patients.Methods Clinical data of elderly inpatients who used vancomycin at the Inner Mongolia Autonomous Region People's Hospital from January 2021 to June 2024 were retrospectively collected.The incidence of VA-AKI and the situation of treatment drug monitoring(TDM)were statistically analyzed.LASSO regression was used for feature selection,and this process was repeated 10,000 times.In each iteration,75％of the training samples were randomly selected,and the frequency of each feature being selected was counted.Finally,the features with higher frequency in multiple iterations were selected for model training.The data were divided into training set and test set at an 8∶2 ratio.Four machine learning prediction models,including Logistic regression,random forest,extreme gradient boosting(XGBoost),and support vector machine(SVM),were established.The accuracy and area under the receiver operating characteristic curve(AUC)of the above prediction models were calculated in the test set.The minimum depth distribution was used to visualize the importance of the characteristics of the model.Results A total of 305 elderly patients receiving vancomycin were included,among which 49 cases(16.07％)developed VA-AKI.LASSO regression analysis selected 7 characteristic variables to build 4 machine learning models,and finally selected the random forest model as the risk prediction model.The random forest model has an AUC value of 0.91,an accuracy of 0.89,an accuracy of 0.88,a recall rate of 0.98,and an F1 value of 0.93.The predictor importance ranking was in order of post-treatment creatinine level,C-reactive protein(CRP),albumin(Alb),respiratory failure,cardiac insufficiency,trough concentration time,and dose.Conclusion Post-treatment creatinine level,respiratory weakness,trough concentration time,cardiac insufficiency,Alb,CRP,and dosage were the risk factors for VA-AKI.The random forest model is the most effective in predicting the risk of VA-AKI in elderly patients,providing a reference for rational use of vancomycin in elderly patients.

Objective To investigate the key factors influencing the willingness of chronic disease patients to participate in home pharmaceutical services.Methods The study adopted the data from inner Mongolia and northeast China set of the drug aging system research for China.The Null Importance method was employed to identify key factors influencing the willingness of chronic disease patients to participate in home pharmaceutical services.The logistic regression model was constructed and evaluated the impact of feature selection through 5 fold cross-validation and accuracy and AUC values.Results 10 key factors were selected by the Null Importance method and the performance of the logistic regression model was improved after feature selection.The factors which significantly affected patients' willingness to accept home pharmaceutical services included the number of accessible information sources(OR=1.261,95％CI=1.182～1.345),medication therapeutic indication cognition(OR=1.342,95％CI=1.124～1.603),the presence the drug packaging or not(OR=1.218,95％CI=1.015～1.462),medication adherence(OR=0.881,95％CI=0.839～0.925),medication literacy(OR=0.631,95％CI=0.488～0.817),the degree of know of medication guidance services(OR=1.211,95％CI=1.017～1.442).Conclusion The logistic model refined by the Null Importance feature selection method demonstrated good performance and was conducive to analyzing the factors influencing the willingness of chronic disease patients to participate in home pharmaceutical care.

Objective To screen and identify significant influencing factors associated with voriconazole clearance using machine learning algorithms.Methods This study utilized a clinical dataset of elderly patients undergoing voriconazole treatment at our institution.We employed seven feature selection techniques from three categories of methods(filter,wrapper methodsand Embedded methods)to identify crucial influencing factors related to voriconazole clearance.Then six algorithms including Stochastic Gradient Descent Regression(SGDR),Lasso Regression(LassoR),Ridge Regression(RidgeR),Random Forest Regression(RFR),XGBoost Regression(XGBR),and Support Vector Regression(SVR),were applied to identify the best models by 5 fold cross-validation and the mean absolute error.SHAP values were employed to analyze the importance of influencing factors.Results The SVR model outperformed other regressors and were considered.The model was developed for seven selected features,which demonstrated good precision with an average relative error was 32.57%,and with approximately 57.89%of predicted values falling within a relative error range of±20%.The SHAP results revealed the importance ranking of influencing factors as ALT,ALP,PLT,administration method,CREA,TBIL,and PCT.Conclusion Feature selection techniques applied in machine learning can be utilized for the screening of influencing factors linked to voriconazole clearance.

OBJECTIVE To evaluate the efficacy and safety of three aromatase inhibitors(exemestane,anastrozole,letrozole)for postmenopausal hormone receptor(HR)-positive early breast cancer.METHODS PubMed,the Cochrane Library,Embase,CNKI,Wanfang Data,VIP and SinoMed were searched to collect randomized controlled trials(RCTs)of the above three drugs in the treatment of postmenopausal HR-positive early breast cancer patients.The retrieval time limit was from the establishment of the database to October 25,2024.After literature screening,data extraction and literature quality evaluation,network meta-analysis was performed by using RevMan 5.3 and Stata 18.0 software.RESULTS A total of 15 RCTs involving 44 055 patients were included.The results of network meta-analysis showed that the objective response rate of letrozole group was significantly higher than anastrozole group(P＜0.05),and the order of surface under the cumulative ranking curve(SUCRA)from high to low was letrozole(85.6%)＞anastrozole(61.5%)＞exemestane(2.8%).The disease-free survival rate of anastrozole group was significantly higher than exemestane and placebo groups(P＜0.05),and the order of SUCRA from high to low was letrozole(85.8%)＞anastrozole(67.3%)＞exemestane(41.4%)＞placebo(5.5%).The total incidence of adverse reactions in anastrozole group was significantly higher than letrozole and placebo groups(P＜0.05),and the order of SUCRA from high to low was exemestane(87.4%)＞letrozole(63.9%)＞anastrozole(47.0%)＞placebo(1.7%).The results of subgroup analysis according to the course of treatment≥104 weeks were consistent with them.CONCLUSIONS Compared with anastrozole,letrozole has better efficacy and safety in the treatment of postmenopausal HR-positive early breast cancer,and the efficacy of exemestane is limited.

Objective To screen and identify significant influencing factors associated with voriconazole clearance using machine learning algorithms.Methods This study utilized a clinical dataset of elderly patients undergoing voriconazole treatment at our institution.We employed seven feature selection techniques from three categories of methods(filter,wrapper methodsand Embedded methods)to identify crucial influencing factors related to voriconazole clearance.Then six algorithms including Stochastic Gradient Descent Regression(SGDR),Lasso Regression(LassoR),Ridge Regression(RidgeR),Random Forest Regression(RFR),XGBoost Regression(XGBR),and Support Vector Regression(SVR),were applied to identify the best models by 5 fold cross-validation and the mean absolute error.SHAP values were employed to analyze the importance of influencing factors.Results The SVR model outperformed other regressors and were considered.The model was developed for seven selected features,which demonstrated good precision with an average relative error was 32.57%,and with approximately 57.89%of predicted values falling within a relative error range of±20%.The SHAP results revealed the importance ranking of influencing factors as ALT,ALP,PLT,administration method,CREA,TBIL,and PCT.Conclusion Feature selection techniques applied in machine learning can be utilized for the screening of influencing factors linked to voriconazole clearance.