Search

Background: Missing data is frequently an inevitable issue in cohort studies and it can adversely affect the study's findings. We assess the effectiveness of eight frequently utilized statistical and machine learning (ML) imputation methods for dealing with missing data in predictive modelling of cohort study datasets. This evaluation is based on real data and predictive models for cardiovascular disease (CVD) risk. Methods: The data is from a real-world cohort study in Xinjiang, China. It includes personal information, physical examination data, questionnaires, and laboratory biochemical results from 10,164 subjects with a total of 37 variables. Simple imputation (Simple), regression imputation (Regression), expectation-maximization(EM), multiple imputation (MICE) , K nearest neighbor classification (KNN), clustering imputation (Cluster), random forest (RF), and decision tree (Cart) were the chosen imputation methods. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) are utilised to assess the performance of different methods for missing data imputation at a missing rate of 20%. The datasets processed with different missing data imputation methods were employed to construct a CVD risk prediction model utilizing the support vector machine (SVM). The predictive performance was then compared using the area under the curve (AUC). Results: The most effective imputation results were attained by KNN (MAE: 0.2032, RMSE: 0.7438, AUC: 0.730, CI: 0.719-0.741) and RF (MAE: 0.3944, RMSE: 1.4866, AUC: 0.777, CI: 0.769-0.785). The subsequent best performances were achieved by EM, Cart, and MICE, while Simple, Regression, and Cluster attained the worst performances. The CVD risk prediction model was constructed using the complete data (AUC:0.804, CI:0.796-0.812) in comparison with all other models with p<0.05. Conclusion: KNN and RF exhibit superior performance and are more adept at imputing missing data in predictive modelling of cohort study datasets. [ABSTRACT FROM AUTHOR]

Background: Metabolic dysfunction-associated fatty liver disease (MAFLD) is the most common chronic liver disease in China. Our study aimed to evaluate the screening value of the fatty liver index (FLI), hepatic steatosis index (HSI), lipid accumulation product (LAP), visceral adiposity index (VAI), and Zhejiang University index (ZJU), as well as other single indicators for MAFLD. We aimed to find the optimal screening tool and its appropriate cut-off values for rural Uyghur adults. Methods: We completed a survey of 14,321 Uyghur adults in 51 groups in Kashgar, Xinjiang, in 2016 using a typical sampling method, with 12,794 patients ultimately included in statistical analyses. Fatty liver was diagnosed using ultrasonography. Results: The prevalence of fatty liver disease (FLD) and MAFLD was 16.73% and 16.55%, respectively, and the FLI, HSI, LAP, VAI, and ZJU were all independently associated with an increased risk of MAFLD. The areas under the receiver operating characteristic curves (AUCs) of the FLI for diagnosing MAFLD in men and women were 0.853 and 0.847, respectively. The AUCs of the body mass index (BMI) for diagnosing MAFLD in men and women were 0.850 and 0.852, respectively. Compared with other metabolic-related markers, FLI had the largest AUC. In men, the optimal cut-off values of FLI and BMI for diagnosing MAFLD were 45 (sensitivity 84.83%, specificity 69.57%) and 27.4 (sensitivity 78.47%, specificity 76.30%), respectively. In women, the optimal cut-off values of FLI and BMI for diagnosing MAFLD were 45 (sensitivity 80.11%, specificity 74.23%) and 28.0 (sensitivity 79.56%, specificity 75.41%), respectively. In men and women, an FLI score of < 30 ruled out MAFLD, while a score of ≥ 50 was a basis for diagnosis. Conclusion: FLI and BMI had good screening ability for MAFLD and were superior to HSI, LAP, VAI, and ZJU in both sexes. [ABSTRACT FROM AUTHOR]

Purpose: With the increase in aging and cardiovascular risk factors, the morbidity and mortality of atherosclerotic cardiovascular disease (ASCVD), represented by ischemic heart disease and stroke, continue to rise in China. For better prevention and intervention, relevant guidelines recommend using predictive models for early detection of ASCVD high-risk groups. Therefore, this study aims to establish a population ASCVD prediction model in rural areas of Xinjiang using survival analysis. Methods: Baseline cohort data were collected from September to December 2016 and followed up till June 2022. A total of 7975 residents (4054 males and 3920 females) aged 30–74 years were included in the analysis. The data set was divided according to different genders, and the training and test sets ratio was 7:3 for different genders. A Cox regression, Lasso-Cox regression, and random survival forest (RSF) model were established in the training set. The model parameters were determined by cross-validation and parameter tuning and then verified in the training set. Traditional ASCVD prediction models (Framingham and China-PAR models) were constructed in the test set. Different models' discrimination and calibration degrees were compared to find the optimal prediction model for this population according to different genders and further analyze the risk factors of ASCVD. Results: After 5.79 years of follow-up, 873 ASCVD events with a cumulative incidence of 10.19% were found (7.57% in men and 14.44% in women). By comparing the discrimination and calibration degrees of each model, the RSF showed the best prediction performance in males and females (male: Area Under Curve (AUC) 0.791 (95%CI 0.767,0.813), C statistic 0.780 (95%CI 0.730,0.829), Brier Score (BS):0.060, female: AUC 0.759 (95%CI 0.734,0.783) C statistic was 0.737 (95%CI 0.702,0.771), BS:0.110). Age, systolic blood pressure (SBP), apolipoprotein B (APOB), Visceral Adiposity Index (VAI), hip circumference (HC), and plasma arteriosclerosis index (AIP) are important predictors of ASCVD in the rural population of Xinjiang. Conclusion: The performance of the ASCVD prediction model based on the RSF algorithm is better than that based on Cox regression, Lasso-Cox, and the traditional ASCVD prediction model in the rural population of Xinjiang. [ABSTRACT FROM AUTHOR]

Background: Gallbladder disease (GBD) can increase the risk of cardiovascular disease (CVD). However, GBD has rarely been reported in the less developed, rural areas of Xinjiang. This study aimed to determine the prevalence of GBD and incidence of CVD in a prospective cohort study in rural Xinjiang. Moreover, the study aimed to explore the association between GBD and CVD within this cohort. Methods: The study cohort included 11,444 Uyghur adults in Xinjiang, 3rd division, from the 51st Mission. Study groups were classified according to whether GBD was present or absent at baseline. The occurrence of CVD was the end event. Demographic, anthropometric, and biochemical data were recorded, and the incidence of CVD in the GBD and non-GBD groups analysed. Cox proportional hazards regression models were used to assess the association between GBD and CVD and factors associated with their incidence. Several subgroup analyses were performed to assess CVD incidence in different subgroups. The interaction between GBD and cardiometabolic risk factors, and subsequent risk of developing CVD, was evaluated. Results: Prevalence of GBD in the study cohort was 10.29%. After a median follow-up of 4.92 years, the cumulative incidence of CVD in the study cohort was 10.49%, 8.43% in males and 12.65% in females. CVD incidence was higher in the GBD group (34.04% vs. 7.78%, HR = 4.96, 95% CI: 4.40–5.59). After multivariate adjustment, the risk of CVD remained higher in the GBD group (HR = 2.89, 95% CI: 2.54–3.29). Subgroup analyses showed male sex, smoking, alcohol consumption, lack of exercise, and abnormal renal function were all associated with increased risk of CVD. Moreover, the risk of CVD was markedly higher in GBD combined with cardiometabolic risk factors (hypertension, T2DM, dyslipidaemia, overweight, and abdominal obesity), than in cardiometabolic risk factors alone and this was higher in the GBD group than in the non-GBD group regardless of whether cardiometabolic risk factors were combined. Conclusion: GBD is an important independent risk factor for CVD development. Awareness of these associations will raise concerns among clinicians about the risk of cardiovascular disease in patients with GBD. [ABSTRACT FROM AUTHOR]

Purpose: To explore the association between waist circumference (WC), estimated cardiopulmonary function (eCRF), and cardiovascular disease (CVD) risk in southern Xinjiang. Update the Framingham model to make it more suitable for the southern Xinjiang population.Methods: Data were collected from 7705 subjects aged 30-74 years old in Tumushuke City, the 51st Regiment of Xinjiang Production and Construction Corps. CVD was defined as an individual's first diagnosis of non-fatal acute myocardial infarction, death from coronary heart disease, and fatal or non-fatal stroke. The Cox proportional hazards regression analysis was used to analyze the association between WC, eCRF and CVD risk. Restricted cubic spline plots were drawn to describe the association of the two indicators with CVD risk. We update the model by incorporating the new variables into the Framingham model and re-estimating the coefficients. The discrimination of the model is evaluated using AUC, NRI, and IDI metrics. Model calibration is evaluated using pseudo R2 values.Results: WC was an independent risk factor for CVD (multivariate HR: 1.603 (1.323, 1.942)), eCRF was an independent protective factor for CVD (multivariate HR: 0.499 (0.369, 0.674)). There was a nonlinear relationship between WC and CVD risk (nonlinear χ2 = 12.43, P = 0.002). There was a linear association between eCRF and CVD risk (non-linear χ2 = 0.27, P = 0.6027). In the male, the best risk prediction effect was obtained when WC and eCRF were added to the model (AUC = 0.763((0.734,0.792)); pseudo R2 = 0.069). In the female, the best risk prediction effect was obtained by adding eCRF to the model (AUC = 0.757 (0.734,0.779); pseudo R2 = 0.107).Conclusion: In southern Xinjiang, WC is an independent risk factor for CVD. eCRF is an independent protective factor for CVD. We recommended adding WC and eCRF in the male model and only eCRF in the female model for better risk prediction. [ABSTRACT FROM AUTHOR]

A body shape index (ABSI) has been proven to be related to a population's CVD incidence. However, the application of this indicator has produced different results. This study aimed to evaluate the applicability of the ABSI in predicting the incidence of CVD in rural Xinjiang, China, and compare it with waist circumference (WC), waist-to-hip ratio (WHR), waist-to-height ratio (WHtR), and body mass index (BMI). 5375 people aged 18 years or older were included in the study. We used the Cox proportional hazard model to evaluate the relationship between WC, WHR, WHtR, BMI, and ABSI and the incidence of CVD, the area under the curve (AUC) to evaluate the predictive power of each anthropometric index for the incidence of CVD, and restricted cubic splines are used to analyse the trend relationship between anthropometric indicators and the incidence of CVD. After multivariate adjustment, standardised WC, WHR, WHtR, BMI, and ABSI all positively correlated with the incidence of CVD. WC had the highest HR (95% CI) value, 1.64 (1.51–1.78), and AUC (95% CI) value, 0.7743 (0.7537–0.7949). ABSI had the lowest HR (95% CI) value, 1.21(1.10–1.32), and AUC (95% CI) value, 0.7419 (0.7208–0.7630). In the sex-specific sensitivity analysis, the predictive ability of traditional anthropometric indicators for the incidence of CVD is higher than that of ABSI. In the rural areas of Xinjiang, the traditional anthropometric indicators of WC had better ability to predict the incidence of CVD than ABSI. [ABSTRACT FROM AUTHOR]

Background: We aimed to identify the relationship between metabolically healthy obesity (MHO), a special subtype of obesity, and the incidence of cardiovascular disease (CVD) in rural Xinjiang. Methods: Body mass index (BMI) and the Joint Interim Statement criteria were utilized to define obesity and metabolic status, respectively. A baseline survey was conducted between 2010 and 2012. The cohort was followed-up until 2017, including 5059 participants (2953 Uyghurs and 2106 Kazakhs) in the analysis. Results: During 6.78 years of follow-up, 471 individuals developed CVD, 10.8% (n=545) of whom were obese, and the prevalence of MHO and MHNW was 5.2% and 54.5%, respectively. Compared with metabolically healthy normal weight subjects, the subjects with MHO had an increased risk of CVD (hazard ratio [HR]=1.76, 95% confidence interval [CI]: 1.23− 2.51), while the metabolically unhealthy obesity (MUO) group had an even higher risk (HR=3.80, 95% CI: 2.87− 5.03). Additionally, there were sex differences in the relationship between BMI-metabolic status and incident CVD (Pinteraction =0.027). Compared with the subjects with MHO, those with MUO had an increased risk of CVD (HR=1.84, 95% CI: 1.26− 2.71). Conclusion: MHO was associated with a high risk of CVD among adults in rural Xinjiang. In each BMI category, metabolically unhealthy subjects had a higher risk of developing CVD than did metabolically healthy subjects. [ABSTRACT FROM AUTHOR]

Background: This cohort study created a risk equation of CVD for the Uyghur and Kazakh ethnic groups with metabolic syndrome (MetS) in Xinjiang and its associated factors, evaluated the model's feasibility, and provided theoretical support for the prevention and early diagnosis of CVD. Methods: A total of 5655 participants from Xinyuan and Jiashi counties in Xinjiang from 2010 to 2012 were selected, including 3770 and 1885 training and validation samples, respectively. A factor analysis was performed on 975 patients with MetS in the training sample, whereas potential factors related to CVD were extracted from 21 MetS biomarkers. Cox regression was used to create and verify a CVD-risk prediction model based on training samples. The receiver operating characteristic curve was drawn to evaluate the model's prediction efficiency. Results: The cumulative incidence of CVD was 9.20% (training sample, 9.12%; validation sample, 9.36%). Nine potential factors were extracted from the training sample population with MetS to predict the CVD risk: lipid (hazard ratio [HR], 1.205), obesity (HR, 1.047), liver function (HR, 1.042), myocardial enzyme (HR, 1.008), protein (HR, 1.024), blood pressure (HR, 1.027), liver enzyme (HR, 1.012), renal metabolic (HR, 1.015), and blood glucose (HR, 1.010). The area under the curve of the training and validation samples was 0.841 (95% confidence interval [CI], 0.821– 0.861) and 0.889 (95% CI, 0.870– 0.909), respectively. Conclusion: The CVD prediction model created with nine potential factors in patients with MetS in Kazakh and Uyghur has a good predictive power. [ABSTRACT FROM AUTHOR]

Background: Few studies have focused on the predictive ability of visceral obesity-related indices for metabolic syndrome (MetS), especially in different ethnic groups. This study aimed to evaluate the applicability of visceral obesity-related indices for MetS screening among three major ethnic groups living in remote rural areas of Xinjiang. Methods: Based on multistage stratified cluster random sampling method, 3,192 Uyghurs, 3,054 Kazakhs, and 3,658 Hans were recruited from Xinjiang, China. The Joint Interim Statement (JIS) criteria were used to define MetS. The receiver operating characteristic curve (ROC), area under the ROC curve (AUC), and predictive value of each visceral obesity-related index were used to evaluate the predictive ability of MetS. Results: After adjusting for potential confounding factors, the lipid accumulation product (LAP), Chinese visceral adiposity index (CVAI), waist-to-height ratio (WHtR), and atherogenic index of plasma (AIP) were significantly correlated with MetS for each ethnic group, and the odds ratios (ORs) for MetS increased across quartiles. LAP was best able to identify MetS status in Kazakhs (AUC=0.853) and Uyghurs (AUC=0.851), with optimal cut-offs being 36.3 and 28.2, respectively. Both LAP (AUC=0.798) and CVAI (AUC=0.791) most accurately identified MetS status in Hans, with the optimal cut-offs being 27.3 and 85.0, respectively. Moreover, the AUC of the combination of these visceral obesity-related indices is higher for each ethnic group. However, compared with LAP, the improved value of combined screening was not significant. Conclusion: LAP had the best discriminative capability for the screening of MetS among Kazakhs, Uyghurs, and Hans. The screening ability of CVAI for MetS was similar to that of LAP in Hans. Thus, LAP may be a complementary indicator for assessing MetS in various ethnic groups. [ABSTRACT FROM AUTHOR]