Objective To construct an XGBoost predictive model using clinical characteristic data from patients with chronic obstructive pulmonary disease(COPD)and evaluate the efficacy of the predictive model in early risk prediction of lung cancer occurrence in COPD patients.Methods In this retrospective cross-sectional study,cluster sampling was used.We selected clinically diagnosed COPD patients admitted to The Second Affiliated Hospital of Xi'an Jiaotong University from January 1,2018,to December 31,2022.A total of 4 008 patients with complete data were included.First,the baseline of each characteristic was analyzed,and then XGBoost was used to construct the lung cancer risk prediction model for COPD patients,and SHAP(SHapley Additive exPlanation)value was used to quantify and attribute the importance of each characteristic.DC A curve was used to evaluate the clinical application value.Results After constructing a lung cancer risk model for COPD patients using 28 variables,eight variables were selected according to the importance of the variables and clinical experience,and the prediction model was reconstructed.The model efficacy in the training set and the test set was 0.948(0.938,0.958)and 0.797(0.738,0.856),respectively.SHAP diagram showed that elevated CEA,CA125,FIB,eosinophils,PLT and D-dimer and reduced TT all contributed to an increased risk of lung cancer in COPD patients.DCA curve showed that the prediction model had clinical application value,which could help doctors make more accurate prognosis prediction and treatment decisions.Conclusion The successful establishment of an XGBoost predictive model,utilizing a subset of features,enables early prediction of lung cancer occurrence in COPD patients.

Objective To construct an XGBoost predictive model using clinical characteristic data from patients with chronic obstructive pulmonary disease(COPD)and evaluate the efficacy of the predictive model in early risk prediction of lung cancer occurrence in COPD patients.Methods In this retrospective cross-sectional study,cluster sampling was used.We selected clinically diagnosed COPD patients admitted to The Second Affiliated Hospital of Xi'an Jiaotong University from January 1,2018,to December 31,2022.A total of 4 008 patients with complete data were included.First,the baseline of each characteristic was analyzed,and then XGBoost was used to construct the lung cancer risk prediction model for COPD patients,and SHAP(SHapley Additive exPlanation)value was used to quantify and attribute the importance of each characteristic.DC A curve was used to evaluate the clinical application value.Results After constructing a lung cancer risk model for COPD patients using 28 variables,eight variables were selected according to the importance of the variables and clinical experience,and the prediction model was reconstructed.The model efficacy in the training set and the test set was 0.948(0.938,0.958)and 0.797(0.738,0.856),respectively.SHAP diagram showed that elevated CEA,CA125,FIB,eosinophils,PLT and D-dimer and reduced TT all contributed to an increased risk of lung cancer in COPD patients.DCA curve showed that the prediction model had clinical application value,which could help doctors make more accurate prognosis prediction and treatment decisions.Conclusion The successful establishment of an XGBoost predictive model,utilizing a subset of features,enables early prediction of lung cancer occurrence in COPD patients.

Objective To evaluate the role and efficacy of preventing bone mineral loss in patients with endometriosis treated by gonadotrophin-releasing hormone analogues (GnRH-a) combined with addback therapy.Methods Prospective,randomized controlled studies of the use of GnRHa with add-back therapy in treatment of endometriosis were enrolled in this study from Medline,Embase,Cochrane library,China National Knowledge Internet (CNKI),Chinese Biological Medicine Disk (CBM) and Data Base of Wanfang.After quality assessment and data extraction,meta-analysis were conducted in the change of BMD,reproductive hormone (E2) and visual pain score (VAS) by Stata 11.0 software.Results A total of 785patients from 13 randomized controlled trail (RCT) studies enrolled in this study after exclude no following up,poor quality and repeat published studies.377 patients were in group of GnRH-a with add-back treatment and 408 patients were in group of GnRna alone.The findinds were showed in meta-analysis:(1) there was a significant difference in percentage change of bone mineral density (BMD) between two groups,the addback therapy was more effective in prevention of bone loss which was (SMD =0.223,95％ CI:0.003 to 0.443,P =0.047).(2) There was no significant difference in the level of reproductive hormone between two groups (SMD =-0.053,95％ CI:-0.479 to 0.373,P =0.807).(3) There was also no significant difference in the visual pain score between the two groups (SMD =-0.157,95％ CI:-0.474 to 0.160,P=0.332).Conclusions GnRH-a with add-back therapy have been shown to be more effective in preventing loss of BMD than GnRH-a treatment alone.However,the long term effect of preventing BMD should be studied.

Objective To evaluate the effect of pitavastatin on blood glucose in patients with hypercholesterolemia,and to investigate the efficacy of pitavastatin in diabetic patients combined with hypercholesterolemia.Method This study was a 12-week,multi-center,open-label,without parallel-group comparison,phase Ⅳ clinical trail.Results Contrasting to baseline,the prevalences at week 4 and 12 post-treatment of abnormal fasting plasma glucose (FPG) and glycosylated hemoglobin Alc (HbA1c)( FPG:14.2％ vs 14.1％ and 11.0％ ; HbA1c:14.3％ vs 15.1％ and 16.1％ ) in the safety set subjects without diabetes mellitus (DM),as well as in those with DM but not taking glucose-lowering drugs (FPG:7/7 vs 4/7 and 5/7; HbAlc:5/5 vs 4/4 and 5/5) had no significant changes (all P vaules ＞0.05).Contrasting to baseline,the levels of TC [ (6.51±0.94) mmol/L vs (5.12 ±0.93) mmol/L and (4.54 ±1.00) mmol/L],LDL-C [(4.11 ±0.79)mmol/L vs (3.02 ±0.81) mmol/L and (2.51 ±0.70)mmol/L] and TG [2.10(1.53,2.54) mmol/L vs 1.62(1.26,2.00) mmol/L and 1.35(1.10,1.86)mmol/L]at week 4 and 12 post-treatment in the per protocol set 55 subjects with DM were significantly reduced (all P values ＜ 0.05 ) ; 33.3％ of subjects at high risk and 10.0％ of subjects at very high risk had achieved a TC target value; 55.6％ of subjects at high risk and 40.0％ of subjects at very high risk had achieved a LDL-C target value.Conclusion Pitavastatin has a safe effect on blood glucose and it could be used to treat diabetic patients combined with hypercholesterolemia in China.