Objective Genome structural equation modeling(GSEM)was used to study the shared genetic structure between Alzheimer's disease(AD)and eight cardiovascular diseases(CVD).Methods In this study,based on AD and CVD data from large consortia and genome-wide association studies,we used chained unbalanced score regression to assess the genetic correlation between the diseases;GSEM was introduced to cross-validate with exploratory factor analysis at odd chromosomes and validation factor analysis at even chromosomes,and pathway analysis was combined to establish three-factor,cofactor,and bifactorial models,so as to reveal the complex genetic relationships between the diseases.Additionally,a cross-validation was performed by swapping the positions of odd and even chromosomes.Results The nine selected diseases can be explained by a three-factor model consisting of three independent factors;a cofactor model explains the relationship between a cofactor and each disease;and an extended two-factor model(a combination of the three-factor model and the cofactor model)performs best in fitting the study data.Conclusion GSEM can be used to explore the shared genetic structure between AD and CVD to discover their interactions,laying a methodological foundation for understanding the genetic relationship between complex diseases.

Objective The Bayesian joint model was applied to predict conversion from mild cognitive impairment(MCI)to Alzheimer's disease(AD),and to compare time effect in longitudinal outcomes,and functional forms for the longitudinal outcomes that are included in the survival model.Methods The longitudinal sub-model used generalized linear mixed models to model the trajectory of longitudinal neuropsychological tests changes pattern,and the survival sub-model adopted a Cox proportional risk model.The longitudinal sub-model utilized two forms of effects,t and t2,and the link structures of longitudinal sub-model and survival sub-model adopted three functional forms(updated value,slope,and area).The data were divided into training and validation sets according to 7∶3,the model parameters were estimated based on Bayesian algorithm,and the dynamic AUC was used to evaluate model prediction performance.Results There were 374(54.20％)of 690 patients with MCI progressed to AD during the follow-up period.In training set,the results of Bayesian joint model with a time effect of t and area effect of three longitudinal neuropsychological tests were optimal,with a mean dynamic AUC of 0.8336.The APOEε4 gene and a low functional activities questionary were risk factors for MCI conversion to AD.The dynamic AUCs of the joint model with the t time effects and area effect for longitudinal data were above 0.75 in the validation sets.Conclusion The application of multivariate Bayesian joint model to MCI risk prediction may provide a theoretical basis for individualized interventions for cognitive impairment and inform statistical methods for survival modeling of chronic diseases.

Objective Genome structural equation modeling(GSEM)was used to study the shared genetic structure between Alzheimer's disease(AD)and eight cardiovascular diseases(CVD).Methods In this study,based on AD and CVD data from large consortia and genome-wide association studies,we used chained unbalanced score regression to assess the genetic correlation between the diseases;GSEM was introduced to cross-validate with exploratory factor analysis at odd chromosomes and validation factor analysis at even chromosomes,and pathway analysis was combined to establish three-factor,cofactor,and bifactorial models,so as to reveal the complex genetic relationships between the diseases.Additionally,a cross-validation was performed by swapping the positions of odd and even chromosomes.Results The nine selected diseases can be explained by a three-factor model consisting of three independent factors;a cofactor model explains the relationship between a cofactor and each disease;and an extended two-factor model(a combination of the three-factor model and the cofactor model)performs best in fitting the study data.Conclusion GSEM can be used to explore the shared genetic structure between AD and CVD to discover their interactions,laying a methodological foundation for understanding the genetic relationship between complex diseases.

Objective The Bayesian joint model was applied to predict conversion from mild cognitive impairment(MCI)to Alzheimer's disease(AD),and to compare time effect in longitudinal outcomes,and functional forms for the longitudinal outcomes that are included in the survival model.Methods The longitudinal sub-model used generalized linear mixed models to model the trajectory of longitudinal neuropsychological tests changes pattern,and the survival sub-model adopted a Cox proportional risk model.The longitudinal sub-model utilized two forms of effects,t and t2,and the link structures of longitudinal sub-model and survival sub-model adopted three functional forms(updated value,slope,and area).The data were divided into training and validation sets according to 7∶3,the model parameters were estimated based on Bayesian algorithm,and the dynamic AUC was used to evaluate model prediction performance.Results There were 374(54.20％)of 690 patients with MCI progressed to AD during the follow-up period.In training set,the results of Bayesian joint model with a time effect of t and area effect of three longitudinal neuropsychological tests were optimal,with a mean dynamic AUC of 0.8336.The APOEε4 gene and a low functional activities questionary were risk factors for MCI conversion to AD.The dynamic AUCs of the joint model with the t time effects and area effect for longitudinal data were above 0.75 in the validation sets.Conclusion The application of multivariate Bayesian joint model to MCI risk prediction may provide a theoretical basis for individualized interventions for cognitive impairment and inform statistical methods for survival modeling of chronic diseases.

Objective The adaptive synthetic sampling(ADASYN)algorithm and category inverse proportion weighting method weighting method were used to balance the datasets,then multi-classification prediction of cognitive normal(CN),mild cognitive impairment(MCI),and Alzheimer's disease(AD)combined with classifiers were performed.Methods Data were obtained from the Alzheimer's Disease Neuroimaging Initiative(ADNI)database,which was filled in missing values by random forest(RF),and feature subsets were selected by elastic net(EN).We chose ADASYN algorithm and category inverse proportion weighting method processing the category imbalance data,and four models were constructed by combining RF and support vector machine(SVM)respectively:ADASYN-RF,ADASYN-SVM,weighted random forest(WRF),and weighted support vector machine(WSVM).We evaluated the classification performance by macro-P,macro-R,macro-F1,ACC,Kappa value and area under the receiver operating characteristics curve(AUC).Results ADASYN-RF had the best classification performance(Kappa=0.938,AUC=0.980),followed by ADASYN-SVM.The most important classification features obtained using ADASYN-RF were CDRSB,LDELTOTAL,and MMSE,which have been clinically validated.Conclusions Both the ADASYN algorithm and the category inverse proportion weighting method can assist in improving classifier performance,and the ADASYN algorithm is superior.

Objective:To explore and analyze the predictive value of EuroSCORE Ⅱ and SYNTAX Ⅱ scores for clinical outcomes in patients undergoing coronary artery bypass grafting (CABG) surgery.Methods:A total of 500 coronary artery disease (CAD) patients who underwent CABG in Shanxi Cardiovascular Hospital from April 2014 to July 2023 were selected as the study subjects, all patients were given EuroSCORE Ⅱand SYNTAX Ⅱ scores to evaluate the predictive value of EuroSCOREⅡfor perioperative mortality and SYNTAX Ⅱ for 4-year mortality. Univariate and multivariate Logistic analysis were employed to analyze the independent risk factors for perioperative and 4-year mortality.Results:There were 3 deaths during the perioperative period, with a mortality rate of 0.60%, the predicted mortality rate of EuroSCOREⅡwas 1.71%; there were 21 deaths at 4 years after surgery, with a mortality rate of 4.23% and the predicted mortality rate of SYNTAX Ⅱwas 9.02%. Logistic regression analysis showed that left ventricular ejection fraction (LVEF) was the only independent protective factor for perioperative mortality, and advanced age was the only independent risk factor for 4-year postoperative mortality in patients ( P<0.05). The analysis of the working characteristic curve of the subjects found that the area under the receiver operating characteristic curve ( ROC) of EuroSCORE Ⅱ for perioperative mortality was 0.782, and the area under ROC curve of SYNTAX Ⅱfor postoperative 4-year mortality was 0.743. Conclusion:Both EuroSCORE Ⅱand SYNTAX Ⅱhave certain predictive value for perioperative mortality and postoperative 4-year mortality in patients undergoing CABG, respectively, but the predicted mortality rate is relatively higher.

Objective To understand the status quo of medical students' integrity in examinations and to explore the influencing factors. Methods 2013-2015 undergraduate students from Clinical Medi-cine, Preventive Medicine and other professional subjects were included in Shanxi Medical University. A total of 221 questionnaires were issued for each grade by stratified random sampling. The database was built with EpiData 3.1. All statical analyses were performed with SPSS software (version 22.0) by means of chi-square test and binary logistic regression. Results Among the 600 medical students, 16.5% of the students had cheating. A statistically significant difference was observed in the cheating rate among the medical stu-dents in terms of gender, grade, academic performance, medical knowledge, memory, family factors, and invigilators' attitude (P<0.05). Litter pressure from the family, the teacher's proctoring is rigorous invigilation, and top scores were the protective factors for medical students' cheating in exams. Conclusion Through the analysis of the influencing factors for the medical students' integrity in examinations, corresponding measures are formulated to provide reference for relevant medical personnel in various medical colleges and universities.