Objective:This study aims to develop a laboratory-based predictive model for early neurological deterioration (END) in patients with acute cerebral infarction (ACI) using baseline data collected at hospital admission.Methods:This study was a retrospective cohort study. Clinical and baseline laboratory test data from 502 patients with ACI admitted to the Department of Neurology at our hospital between January 1, 2022 and May 31, 2025. Of these patients, 313 were male and 189 were female, with a median age of 67 years (interquartile range: 58-73). Patients were classified into an END group and a non-END group according to the occurrence of END within 7 days of admission. Subsequently, using the caret package in R (version 4.4.2), the dataset was randomly divided into a training set ( n=351) and a validation set ( n=151) at a 7∶3 ratio, with END status as the stratification variable and a fixed random seed to ensure reproducibility. Following baseline characteristic comparisons between groups, these datasets were used for model development and validation, respectively. The differences in clinical indicators between the two patients groups were assessed using the chi-square test and the Wilcoxon rank sum test. In the training group, Lasso regression was utilized to identify variables significantly associated with END. Seven machine learning algorithms-decision tree (DT), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), K-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR)-were employed to develop predictive models. The optimal hyperparameters were determined via grid search integrated with 5-fold cross-validation. The final algorithm was selected based on comprehensive model performance evaluation. Additionally, clinical data of 79 patients with ACI, collected between June 1 to August 31, 2025, were compiled as an independent test set for external validation. The cohort comprised 49 males and 30 females, with a median age of 68 years (interquartile range: 57-72). The SHapley Additive exPlanations (SHAP) method was employed to access feature importance and model interpretability. SHAP dependence plots and interaction plots were utilized to emplore the nonlinear relationships and interaction effects among the featurevariables. Results:Among the 502 patients, 166 experienced END during 7 days of hospitalization. Lasso regression identified nine significant predictors: history of hyperlipidemia, admission NIHSS score, lymphocyte-to-monocyte ratio (LMR), hemoglobin, D-dimer, albumin, neuron-specific enolase (NSE), homocysteine (HCY), and vitamin B12. The area under the receiver operating characteristic curve (AUC) for the seven machine learning models ranged from 0.709 to 0.946. The XGB model achieved the highest predictive performance, with an AUC of 0.946 (95% CI 0.924-0.960) in the training cohort and 0.867 (95% CI 0.902-0.933) in the validation cohort. SHAP analysis revealed that the top five variables contributing to END prediction were admission NIHSS score, HCY, D-dimer, history of hyperlipidemia, and vitamin B12. Conclusion:This study successfully developed a laboratory-based prediction model for END using the XGB machine learning algorithm, which demonstrated strong predictive performance.

Objective:This study aims to develop a laboratory-based predictive model for early neurological deterioration (END) in patients with acute cerebral infarction (ACI) using baseline data collected at hospital admission.Methods:This study was a retrospective cohort study. Clinical and baseline laboratory test data from 502 patients with ACI admitted to the Department of Neurology at our hospital between January 1, 2022 and May 31, 2025. Of these patients, 313 were male and 189 were female, with a median age of 67 years (interquartile range: 58-73). Patients were classified into an END group and a non-END group according to the occurrence of END within 7 days of admission. Subsequently, using the caret package in R (version 4.4.2), the dataset was randomly divided into a training set ( n=351) and a validation set ( n=151) at a 7∶3 ratio, with END status as the stratification variable and a fixed random seed to ensure reproducibility. Following baseline characteristic comparisons between groups, these datasets were used for model development and validation, respectively. The differences in clinical indicators between the two patients groups were assessed using the chi-square test and the Wilcoxon rank sum test. In the training group, Lasso regression was utilized to identify variables significantly associated with END. Seven machine learning algorithms-decision tree (DT), random forest (RF), light gradient boosting machine (LGBM), extreme gradient boosting (XGB), K-nearest neighbors (KNN), support vector machine (SVM), and logistic regression (LR)-were employed to develop predictive models. The optimal hyperparameters were determined via grid search integrated with 5-fold cross-validation. The final algorithm was selected based on comprehensive model performance evaluation. Additionally, clinical data of 79 patients with ACI, collected between June 1 to August 31, 2025, were compiled as an independent test set for external validation. The cohort comprised 49 males and 30 females, with a median age of 68 years (interquartile range: 57-72). The SHapley Additive exPlanations (SHAP) method was employed to access feature importance and model interpretability. SHAP dependence plots and interaction plots were utilized to emplore the nonlinear relationships and interaction effects among the featurevariables. Results:Among the 502 patients, 166 experienced END during 7 days of hospitalization. Lasso regression identified nine significant predictors: history of hyperlipidemia, admission NIHSS score, lymphocyte-to-monocyte ratio (LMR), hemoglobin, D-dimer, albumin, neuron-specific enolase (NSE), homocysteine (HCY), and vitamin B12. The area under the receiver operating characteristic curve (AUC) for the seven machine learning models ranged from 0.709 to 0.946. The XGB model achieved the highest predictive performance, with an AUC of 0.946 (95% CI 0.924-0.960) in the training cohort and 0.867 (95% CI 0.902-0.933) in the validation cohort. SHAP analysis revealed that the top five variables contributing to END prediction were admission NIHSS score, HCY, D-dimer, history of hyperlipidemia, and vitamin B12. Conclusion:This study successfully developed a laboratory-based prediction model for END using the XGB machine learning algorithm, which demonstrated strong predictive performance.

Objective To investigate the relationship of serum 25-hydroxyvitamin D [25(OH)D] level and blood glucose control in patients with type 2 diabetes mellitus (T2DM).Methods The clinical data of 300 pa-tients with T2DM in the hospital were analyzed retrospectively.According to the level of glycated hemoglobin (HbA1c) ,the patients were divided into the good control of blood glucose group (＜6.5%) ,the medium con-trol of blood glucose group (6.5% -7.5%) and the poor control of blood glucose group (＞7.5%).Another 44 healthy individuals with normal glucose tolerance (NGT) confirmed by oral glucose tolerance test (OGT T) were selected as normal control group.The level of 25(OH)D in each group was compared ,and the correlation between HbA1c and 25(OH)D was analyzed.Results The level of serum 25(OH)D in the poor control of blood glucose group was significantly lower than that in the good control of blood glucose group and the con-trol group ,and the difference was statistically significant (P＜0.05) ;the levels of serum 25(OH)D in the the medium and good control of blood glucose groups were significantly lower than that in the control group (P＜0.05).HbA1c was negatively correlated with 25 (OH) D level (r= -0.212 ,P=0.000).Conclusion The level of serum 25 (OH) D is related to the development of T2DM.Proper vitamin D supplementation can be used as an adjuvant therapy for T 2DM.

Objective To observe the effect and toxicity of gemcitabine and S-1 in treatment of metastatic triple-negative breast cancer.Methods In this study,41 cases of metastatic breast cancer were treated in the General Hospital of Shenyang Military Region between Jun.2010 and Dec.2012.The median age was 55 years old.The pathological diagnosis of these patients was triple-negative breast cancer.All patients were given gemcitabine 1000 mg/m2 intravenously on the 1st and 8th day,and 60 mg S-1 from the 1st day to the 14th day orally for every cycle.There were 21 days for each cycle.All patients accepted at least 2 cycles of chemotherapy and once effect evaluation.Results 41 cases were diagnosed as metastatic triple-negative breast cancer,with the failure of second-line treatment.The median age was 55 years.All cases were followed up until death.All the 41 cases were administrated for more than 2 cycles,among whom,there were 0 case of complete response(CR),16 cases (39.0％)of partial response(PR),14 cases(34.1％) of stable disease(SD),and 11 cases(26.8％) of progressive disease(PD).The disease control rate was 73.1％ (30/41).In this study,median progression free survival(mPFS)was 7.9 months.The rate of digestive toxicity and marrow suppression was 24.4％ and 55％ respectively.No patient stopped treatment because of severe toxicities.Conclusion The chemotherapy regimen of gemcitabine and S-1 is effective in treatment of metastatic triple-negative breast cancer,and the toxicity could be tolerated.

Objective To investigate the therapeutic effect of ambroxol in bleomycin-induced pulmonary fibrosis of rats.Methods Sixty Wistar rats were divided into three groups:The normal control group(group N),the model group treated with bleomycinA5(group B)and the group treated with ambroxol(group A).Pulmonary fibrosis was induced by intratracheal instillation of bleomycin.Then the rats received daily ambroxol 35mg/kg(group A),or normal saline(group B).Five rats in each group were killed on 3.7.14 and 28 days after intratracheal instillation.Histological changes of the lungs were evaluated by HE stain and Masson's trichrome stain.The levels of tumor necrosis factor-?(TNF-?)in lung homogenates were measured by radioimmunoassay.Results Pulmonary fibrosis of Group A was significantly improved as compared with that of Group B(P

Objective To discuss the effect and feasibility of BiPAP in refractory asthma patients. Methods A total of 15 coses of refractory bronchial asthma admitted by our hospital during Feb 2003 to May 2006 were treated by BiPAP in addition to medical therapy。 The symptoms、signs and the arterial blood gases were observed and analyzed。Results Among 15 patients,2 gave up treatment,13 patients were successfully treated with the BiPAP therapy。There were significant improvement of PaCO2、PaO2、pH and respiratory rate ,heart rate after 2h BiPAP。Conclusions Ventilation in BiPAP is an effective method for refractory asthma ,which can save the patients life and decrease the complications.

Objective To discuss the effect and possibility of NIPPV in ILD combined with respiratory failure. Methods A total of 37 cases of ILD combined with respiratory failure admitted by our hospital during Feb 2004 to Oct 2007 were divided into treatment group (20 cases) and control group (17 cases). Routine pharmaceutical intervention was adopted in both groups while NIPPV was given in the patients of treatment group. The symptoms、signs and the arterial blood gases were observed and analyzed. Results Among 20 patients,3 gave up treatment , 17 patients were successfully treated with the NIPPV therapy. There were significant improvement of PaCO2、PaO2、pH and respiratory rate ,heart rate after 2h NIPPV. Conclusion NIPPV is an effective method for ILD combined with respiratory failure,which can save the patients life and decrease the complications.