Purpose: We aimed to assess if lipid accumulation product (LAP) could outperform body mass index (BMI) as a marker for diabetes diagnosis. Methods: We analyzed the results of a national physical examination project in Urumqi, China. This project was conducted in 442 community clinics in Urumqi from October 2016 to February 2017. Results: LAP was highly correlated with diabetes. The subjects with higher amounts of LAP had a higher risk of diabetes, and the prevalence of diabetes in the fourth quartile of LAP was dramatically higher than in the first quartile (5.72% vs. 21.76%). The adjusted odds ratios (AOR) associated with diabetes in the fourth quartile of LAP was significantly higher than the AOR associated with diabetes in the first quartile, and when BMI ≥ 28 kg/m² was compared with BMI < 28 kg/m² (3.24 (3.11, 3.37) vs. 1.65 (1.60, 1.70)). The LAP’s area under the curve (AUC) was significantly higher than the BMI’s AUC when based on diabetes (0.655 vs. 0.604). In the normal BMI group, 34% of participants had a LAP value higher than the cutoff point found during ROC analysis. In this subgroup, we observed a significantly higher prevalence of diabetes that was similar to that of the subgroup with a BMI ≥ 28 kg/m², and both of their LAP values were higher than the cutoff point. Conclusion: When use as a tool for diabetes diagnosis, LAP performed better than BMI, implying that LAP could be a preferable anthropometry assessment.

Objective. To investigate the prevalence of nonalcoholic fatty liver disease (NAFLD) and the association of serum uric acid level with NAFLD in Uygur people, Xinjiang. Methods. A total of 2241 Uyghur persons (1214 males and 1027 females) were interviewed for physical checkups from 2011 to 2012. The clinical data of questionnaire survey, body mass index (BMI), abdominal circumference, blood pressure, blood sugar, blood lipid, and serum uric acid level were collected for analysis. Results. The prevalence rates of NAFLD determined by abdominal ultrasound examination and hyperuricemia were 43.9% and 8.4%, respectively. The persons with NAFLD had significantly higher serum uric acid levels than those without NAFLD (320 ± 88 versus 254 ± 80μmol/L; ). The prevalence rate of NAFLD was significantly higher in subjects with hyperuricemia than that in those without hyperuricemia (78.19% versus 40.83%; ), and the prevalence rate increased with progressively higher serum uric acid levels (). Multiple regression analysis showed that hyperuricemia was associated with an increased risk of NAFLD (odds ratio (OR): 2.628, 95% confidence interval (CI): 1.6084.294, and ). Conclusion. Serum uric acid level was significantly associated with NAFLD, and the prevalence rate of NAFLD increased with progressively higher serum uric acid levels.

The focus of this study is the use of machine learning methods that combine feature selection and imbalanced process (SMOTE algorithm) to classify and predict diabetes follow-up control satisfaction data. After the feature selection and unbalanced process, diabetes follow-up data of the New Urban Area of Urumqi, Xinjiang, was used as input variables of support vector machine (SVM), decision tree, and integrated learning model (Adaboost and Bagging) for modeling and prediction. The experimental results show that Adaboost algorithm produces better classification results. For the test set, the G-mean was 94.65%, the area under the ROC curve (AUC) was 0.9817, and the important variables in the classification process, fasting blood glucose, age, and BMI were given. The performance of the decision tree model in the test set is relatively lower than that of the support vector machine and the ensemble learning model. The prediction results of these classification models are sufficient. Compared with a single classifier, ensemble learning algorithms show different degrees of increase in classification accuracy. The Adaboost algorithm can be used for the prediction of diabetes follow-up and control satisfaction data.

Background: Genetic polymorphisms of the transcription factor 7-like 2 (TCF7L2) gene have been reported to be strongly associated with type 2 diabetes mellitus (T2DM) in Icelandic, Danish and American populations and further replicated in other European populations, African Americans, Mexican Americans, and Asian populations. The aim of the present study was to investigate the association of TCF7L2 gene polymorphisms with T2DM in a Uygur population of China. Methods: 877 T2DM patients and 871 controls were selected for the present study. Two single nucleotide polymorphisms (SNPs) (rs12255372 and rs7901695) were genotyped by using matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry. The associations of SNPs and haplotypes with T2DM and linkage disequilibrium (LD) structure of the TCF7L2 gene were analyzed. Results: For total participants and male, the distribution of rs12255372 alleles and the dominant model (Guanine Guanine (GG) genotype vs. Guanine Thymine (GT) genotype + Thymine Thymine (TT) genotype) showed significant difference between T2DM and control subjects (for allele: p = 0.013 and p = 0.002, respectively; for dominant model: p = 0.028 and p = 0.008, respectively). The distribution of rs7901695 alleles and the dominant model (TT genotype vs. Thymine Cytosine (TC) genotype + Cytosine Cytosine (CC) genotype) for total participants and male showed significant difference between T2DM and control subjects (for allele: both p = 0.001; for dominant model: p = 0.006 and p = 0.008, respectively). Conclusions: Our data suggested that the genetic polymorphisms of the TCF7L2 gene were associated with T2DM in the Uygur population of China.

Background. An estimated 425 million people globally have diabetes, accounting for 12% of the world’s health expenditures, and the number continues to grow, placing a huge burden on the healthcare system, especially in those remote, underserved areas. Methods. A total of 584,168 adult subjects who have participated in the national physical examination were enrolled in this study. The risk factors for type II diabetes mellitus (T2DM) were identified by p values and odds ratio, using logistic regression (LR) based on variables of physical measurement and a questionnaire. Combined with the risk factors selected by LR, we used a decision tree, a random forest, AdaBoost with a decision tree (AdaBoost), and an extreme gradient boosting decision tree (XGBoost) to identify individuals with T2DM, compared the performance of the four machine learning classifiers, and used the best-performing classifier to output the degree of variables’ importance scores of T2DM. Results. The results indicated that XGBoost had the best performance (accuracy=0.906, precision=0.910, recall=0.902, F‐1=0.906, and AUC=0.968). The degree of variables’ importance scores in XGBoost showed that BMI was the most significant feature, followed by age, waist circumference, systolic pressure, ethnicity, smoking amount, fatty liver, hypertension, physical activity, drinking status, dietary ratio (meat to vegetables), drink amount, smoking status, and diet habit (oil loving). Conclusions. We proposed a classifier based on LR-XGBoost which used fourteen variables of patients which are easily obtained and noninvasive as predictor variables to identify potential incidents of T2DM. The classifier can accurately screen the risk of diabetes in the early phrase, and the degree of variables’ importance scores gives a clue to prevent diabetes occurrence.

Diabetes is a major global public health problem driven by a high prevalence of metabolic risk factors. To describe the differences of metabolic risk factors of type 2 diabetes, as well as glycemic control and complicated diabetic complications between rural and urban Uygur residents in Xinjiang Uygur Autonomous Region of China. This comparative cross-sectional study, conducted among 2879 urban and 918 rural participants in Xinjiang, China, assessed the metabolic risk factors of diabetes and related complications differences between urban and rural settlements. Compared to rural areas, urban participants had higher education level and more average income, little physical activity, less triglycerides and higher HDL-c (p < 0.05 respectively). Differences in metabolic risk factors by urban/rural residence included overweight or obesity, triglycerides (≥1.71mmol/l), HDL-c (< 1.04 mmol/l), alcohol intake, and physical inactivity (p < 0.01 respectively). There was significant difference regarding the prevalence of HbA1c >8% (48.1% versus 54.5%, p = 0.019) between rural and urban diabetic participants. No significant difference in the prevalence of type 2 diabetic complications between urban and rural participants (74.9% versus 72.2%; p = 0.263) was detected. Compared to rural participants, the most prevalent modifiable risk factors associated with diabetic complications in urban participants were obesity (BMI ≥ 28 Kg/m²), HDL-c (< 1.04 mmol/l), physical inactivity and irregular eating habits (p = 0.035, p = 0.001, p < 0.001, and p = 0.013, respectively). Urban settlers were significantly more likely to have metabolic risk factors highlighting the need for public health efforts to improve health outcomes for these vulnerable populations. Diabetes related complications risk factors were prevalent amongst rural and urban diabetes settlers.