Objective To address the limitations of traditional nonparametric methods in analyzing ordinal data,which often overlook nonlinear characteristics and polarization trends,this study explores the application value of dominance analysis and the ANY polarization index in quantifying distributional differences and inequality.Methods Simulated Likert-scale datasets(with varying medians)and real-world data from the National Health and Nutrition Examination Survey(NHANES)were analyzed using dominance analysis and the ANY index.Their performance in revealing distributional heterogeneity and polarization was compared with conventional rank-based tests.Results Dominance analysis effectively distinguished inter-group differences in overall levels(F-dominance)and internal inequality(S-dominance)through cumulative distribution function(CDF).The ANY index captured polarization trends by adjusting parameters α(emphasizing lower percentiles)and β(emphasizing upper percentiles).In NHANES data,the new methods identified significantly higher low-end polarization in males'self-rated health,whereas traditional Mann-Whitney U tests showed no statistical significance.Conclusion Dominance analysis and the ANY index overcome the oversimplified assumptions of conventional methods,offering refined tools for analyzing ordinal data in health policy-making,particularly in optimizing resource allocation and addressing health disparities among vulnerable populations.

Objective This study aimed to explore the feasibility of using a long short-term memory(LSTM)model based on empirical mode decomposition(EMD)and singular spectrum analysis(SSA)to predict the incidence of pulmonary tuberculosis in Shanxi Province.The goal was to provide a reliable prediction method to support the prevention and control of tuberculosis epidemics in the region.Methods Collecting and collating monthly data on the reported incidence of tuberculosis nationwide from January 2007 to December 2018.The LSTM、EMD-LSTM、SSA-LSTM models were established using the reported monthly incidence of tuberculosis reported in Shanxi Province from January 2007 to December 2017 as the training set and using the reported monthly incidence of tuberculosis from January to December 2018 as the test set.Mean squared error(MSE),mean absolute error(MAE),root mean squared error(RMSE),and mean absolute percentage error(MAPE)were used to evaluate the prediction effect of the models to determine the best model.Results The MSE,MAE,RMSE and MAPE of the EMD-LSTM model in predicting the incidence trend of pulmonary tuberculosis in the next year were 0.036,0.140,0.189 and 0.045,respectively.Compared with the LSTM model,the prediction performance increased by 66.36%,38.33%,42.38%and 41.56%,respectively.Compared with the SSA-LSTM model,it improved by 28.00%,9.68%,15.25%and 16.67%,respectively.Conclusion Compared with the single LSTM model,the fitting and prediction performance of EMD-LSTM and SSA-LSTM models are improved effectively.However,the prediction effect of EMD-LSTM model is better than that of SSA-LSTM model.Therefore,the EMD-LSTM model is more suitable for predicting the incidence trend of pulmonary tuberculosis in Shanxi Province,and can provide a theoretical basis for tuberculosis prevention and control policies.

Objective In this study,clinical data of Alzheimer's disease(AD)patients,structural magnetic resonance imaging(sMRI)data,and positron emission tomography(PET)data were used to construct an auxiliary diagnostic model with good classification effects,so as to formulate a personalized treatment plan at the early stage of the patients,which is of great significance for the prevention and treatment of AD.Methods In this study,a total of 401 study subjects containing complete sMRI images and PET images were selected from the ADNI-1(Alzheimer's disease neuroimaging initiative-1,ADNI-1)database.We used statistical parameters mapping(SPM)and voxel-based morphometric(VBM)analysis of MATLAB to perform pre-processing operations such as spatial normalization and skull stripping on sMRI images and PET images of the study subjects.With the help of the brain atlas was used to segment the brain tissue structure.After that,the segmented gray matter was extracted from the corresponding brain regions based on anatomical automatic labeling,and the feature values of all brain regions were obtained.Then the extracted brain region feature values are then subjected to fisher score,support vector machine-recursive feature elimination(SVM-RFE)and least absolute shrinkage and selection operator(LASSO),a hybrid filtered-wrapped-embedded feature selection method with three different principles,to realize the dimensionality reduction of high-dimensional image data.Finally,the PAC-Bayesian strategy boosting based multi-view learning(PB-MVBoost)model is constructed based on multi-view decision fusion for clinical,sMRI and PET data.And it is compared with the traditional machine learning models support vector machine(SVM),decision tree(DT),K-nearest neighbor(KNN),random forests(RF),adaptive boosting(AdaBoost),and extreme gradient boosting(XGBoost)which are constructed after concatenating views.It is compared with multi-view multi-kernel learning models(AverageMKL,EasyMKL)and multi-view confusion matrix boosting,which is also the same multi-view decision fusion.Results Among all the multi-view fusion models of AD-MCI,the PB-MVBoost model based on decision fusion has the best performance(accuracy=0.98,F1-score=0.97,precision=0.98,recall=0.96,MSE=0.07).Among all the multi-view fusion models of MCI-NC,the model performance of PB-MVBoost based on decision fusion was the best(accuracy=0.99,F1-score=0.98,precision=0.99,recall=0.98,MSE=0.05).Conclusion In the classification of AD-MCI and MCI-NC,the distinction and calibration degree of PB-MVBoost model were optimized,indicating that the auxiliary diagnosis model of Alzheimer's disease constructed by PB-MVBoost classifier based on decision fusion performed the best,which could improve the recognition of patients with mild cognitive impairment and then assist clinical diagnosis.

Objective Based on the multi-dimensional postoperative outcomes of patients with percutaneous coronary intervention(PCI)the prediction model of adverse outcomes in patients with coronary heart disease after PCI was constructed by combining multi-label deep forest algorithm.Methods 521 patients diagnosed with coronary heart disease and undergoing PCI from the Second Hospital of Shanxi Medical University were collected.Multi-label ReliefF algorithm was used to filter features,and multi-label-random oversampling algorithm was used to deal with data imbalance.Finally,multi-label deep forest algorithm(MLDF)was used to build a prediction model.Results Multi-label ReliefF was used to filter the characteristics.The results showed that B-type natriuretic peptide,creatine kinase isoenzyme,hemoglobin,homocysteine,C-reactive protein and serum indirect bilirubin were important factors affecting the prognosis of PCI.The MLROS algorithm improved the imbalance of multi-tag data to a certain extent,and the mean IR of the whole tag was reduced from 3.937 to 2.668.Conclusion In this study,the multi-label deep forest algorithm was combined with the adverse outcome of patients after PCI.At the same time,considering the problem of multi-tag feature selection and data imbalance,and fully considering the actual clinical situation,patients may have multiple outcomes at the same time after PCI,which is more in line with the requirements of modern medicine.

Objective To investigate the prevalence of metabolic syndrome(MS)and its influencing factors among adult residents in Zhifu district of Yantai city,and to provide data support and scientific basis for relevant departments to formulate policies and measures.Methods A total of 2412 residents in Zhifu district were selected by multi-stage stratified sampling method,and their basic information,personal health status,height,weight,blood pressure,fasting blood glucose,blood lipids and other indicators were collected by questionnaire survey,physical measurement and laboratory examination.The screening of MS was based on the diagnostic criteria of MS recommended by Chinese Diabetes Society(CDS).Results Among the adult residents in Zhifu district,the number of MS patients was 522,with a crude prevalence rate of 21.6%.The prevalence of MS in men was 26.9%higher than that in women(16.9%)(χ2=35.939,P<0.001).With the increase of age,the prevalence rate of MS showed an overall upward trend(linear trend test χ2=150.557,P<0.001).With the increase of education level,the prevalence rate of MS showed an overall downward trend(linear trend test χ2=81.670,P<0.001).The results of multivariate logistic regression analysis further showed that male and age increase were high risk factors for MS;higher education level,unmarried,engaged in static occupation,and increased activity were protective factors for MS.Conclusion The prevalence rate of MS in adult residents in Zhifu district of Yantai is basically equal to the national average level,suggesting that the government and health service institutions at all levels should take health exercise,smoking cessation and alcohol restriction as the entry point for health education and early diagnosis and treatment;meanwhile,targeted interventions should be carried out according to different characteristics of the population.

Objective This study aimed to explore the underlying mechanisms between parental neglect and depression of adolescents.Methods This study utilized data from the 2020 China Family Panel Studies(CFPS)and included 1902 adolescents aged 10～15.Correlation analysis,multivariable logistic regression,structural equation modeling,and the bootstrap method were employed to examine the relationships between parental neglect,social trust,and depressive symptoms in adolescents.Results This study found that the prevalence of depressive symptoms among adolescents was 10.9%.Parental neglect was associated with an increased risk of depressive symptoms(OR:1.772,95%CI:1.310～2.636),and social trust acted as a mediator between parental neglect and depressive symptoms(mediating effect:17.20%,P<0.001).Additionally,gender moderated the latter half of the mediation model(β:0.127,95%CI:0.016～0.236,P<0.001).Conclusion The experiences of parental neglect are closely related to higher levels of depressive symptoms among adolescents,with social trust serving as a mediating factor.This mediating effect of social trust is particularly significant among females.It is crucial to cultivate a supportive environment and develop a harmonious family atmosphere.

Objective To explore the integrating modeling strategy of prognosis prediction models,and provide support for the methodological selection of establishing effective clinical prediction models.Methods Based on the SEER liver cancer clinical follow-up data,the predictive performance and estimation accuracy of the classical Cox proportional hazard regression model,frequentist model averaging,and Bayesian model averaging methods were compared,and the applicability of model averaging methods was explored.Simulated studies were used to investigate the predictive performance of the models.Results Results of simulation analysis:the C index obtained by Bayesian model averaging was slightly higher than the Cox regression and frequentist model averaging.The 95%confidence interval of the C index tended to become narrower as the sample size increased.For variables with larger effect sizes,the Bayesian model averaging method obtained the smallest deviation of regression coefficients and the largest 95%interval coverage.Results of the case study:the validation set C index obtained by Cox regression,Bayesian model averaging and frequentist model averaging were 0.7845(95%CI:0.7613～0.8076),0.7851(95%CI:0.7619～0.8083)and 0.7845(95%CI:0.7613～0.8076),respectively.Conclusion Bayesian model averaging method can improve the ability of predicting prognosis when the sample size is small and the predictor variables are correlated.

Objective To analyze the status and influencing factors of Helicobacter pylori(Hp)infection in the occupational population of Chengdu city.Methods A retrospective analysis was conducted on the general data of 8860 occupational population who underwent health examinations in our hospital from June 2021 to June 2023.All study subjects underwent 14 C urea breath test during health check ups.Analyze the Hp infection status of 8860 occupational population,and use logistic regression analysis(single factor and multiple factor)to explore the influencing factors of Hp infection in occupational population in Chengdu.Results Among the 8860 occupational population undergoing physical examinations in Chengdu,2890 cases were positive for Hp infection,with a total Hp infection rate of 32.62%.Univariate analysis found that occupational groups with age≥40 years,male,BMI<18.5 kg/m2(underweight)/24.0 kg/m2～27.9 kg/m2(overweight)/≥28 kg/m2(obese),workers,history of alcohol consumption,smoking,unclean diet,family history of Hp infection,and history of spicy and jelly diet had a higher Hp infection rate(P<0.05).Multivariate analysis showed that age≥40 years old,low BMI,overweight,obesity,alcohol consumption history,unclean diet history,family history of Hp infection,and spicy diet history were all risk factors affecting Hp infection in the occupational population of Chengdu(P<0.05).Conclusion The positive rate of Hp infection in the occupational population of Chengdu is relatively high,associated with age,alcohol consumption history,BMI,history of unclean diet,family history of Hp infection,and history of spicy eating.Therefore,attention should be paid to the Hp infection status of the occupational population.It is not only necessary to strengthen Hp infection publicity and education,but also to intervene in its risk factors early,in order to reduce and prevent Hp infection in the occupational population.

Objective To provide a scientific basis for cancer prevention and control in Zhifu district and Yantai city by comprehensively describing and analyzing the epidemiological characteristics and disease burden of malignant tumors in Zhifu district,and reduce the disease burden.Methods The data of cancer incidence and mortality collected by the Center for Disease Control and Prevention in Zhifu district from 2010 to 2020 were used to evaluate the incidence and mortality of cancer.The excel template and DismodII software released by WHO were used to calculate the disease burden indexes such as disability-adjusted life year(DALY),years of life lost(YLL),and DALY rate,and the Joinpoint regression model was used to analyze the trend of disease burden,and annual percent change and average annual percent change were calculated.Results The total DALY of malignant tumors in Zhifu district from 2010 to 2020 was 166192.75 person-years,with a DALY rate of 199.02‰.The disease burden of malignant tumors mainly came from YLL,accounting for 74.70%of DALY.Conclusion Zhifu malignant tumor disease burden is on the rise,the relevant departments still need to improve the registration of malignant tumors,improve the knowledge of the population through the way of public welfare propaganda,increase the screening of common malignant tumors,promote the progress of early diagnosis and treatment of cancer,reduce the disease burden brought by early death.To improve the tertiary prevention of malignant tumors.

Objective To understand the current situation and influencing factors of the quality of life(QOL)of elderly people in Xinjiang,explore the relationship between the quality of life of elderly people,chronic disease comorbidities,and daily living activities,and provide new ideas and reference research for improving the quality of life of elderly people.Methods Stratified cluster random sampling was used,and 2610 permanent elderly population in Urumqi,Aksu,Karamay and Changji of Xinjiang Uygur Autonomous Region were selected in 2023 for questionnaire survey.Results The quality of life score of the elderly was(68.38±20.76),and the comorbidity rate of chronic diseases was 53.1%.Multiple chronic conditions(MCC)had a significant predictive effect on QOL score(β=-4.3497,P<0.001),and activities of daily living(ADL)grading had a significant predictive effect on QOL score(β=0.5534,P<0.001).MCC can affect QOL score through the mediating effect of ADL directly or indirectly.The direct effect(-6.2894)and indirect effect(-1.7820)account for 70.18%and 29.82%of the total effect,respectively.There is a certain mediating effect of ADL between QOL and MCC status in elderly people.Conclusion Chronic comorbidities are significantly negatively correlated with QOL and ADL scores for the elderly.The more chronic diseases,the lower the QOL score and ADL score in the elderly,and the more severe the impairment of daily living ability.