Objective: For the patients who are suffering from type 2 diabetes, blood glucose level could be affected by multiple factors. An accurate estimation of the trajectory of blood glucose is crucial in clinical decision making. Frequent glucose measurement serves as a good source of data to train machine learning models for prediction purposes. This study aimed at using machine learning methods to predict blood glucose for type 2 diabetic patients. We investigated various parameters influencing blood glucose, as well as determined the most effective machine learning algorithm in predicting blood glucose.Patients and methods: 273 patients were recruited in this research. Several parameters such as age, diet, family history, BMI, alcohol intake, smoking status et al were analyzed. Patients who had glycosylated hemoglobin less than 6.5% after 52 weeks were considered as having achieved glycemic control and the rest as not achieving it. Five machine learning methods (KNN algorithm, logistic regression algorithm, random forest algorithm, support vector machine, and XGBoost algorithm) were compared to evaluate their performances in prediction accuracy. R 3.6.3 and Python 3.12 were used in data analysis.Results: The statistical variables for which p< 0.05 was obtained were BMI, pulse, Na, Cl, AKP. Compared with the other four algorithms, XGBoost algorithm has the highest accuracy (Accuracy=99.54% in training set and 78.18% in testing set) and AUC values (1.0 in training set and 0.68 in testing set), thus it is recommended to be used for prediction in clinical practice.Conclusion: When it comes to future blood glucose level prediction using machine learning methods, XGBoost algorithm scores the highest in effectiveness. This algorithm could be applied to assist clinical decision making, as well as guide the lifestyle of diabetic patients, in pursuit of minimizing risks of hyperglycemic or hypoglycemic events.

Background: Changes in vascular function are closely associated with the development of cardiovascular disease (CVD). Pulse wave velocity (PWV) is a potential indicator of vascular dysfunction; it allows noninvasive assessment of arterial stiffness. Currently, evidence for the effects of different classes of antidiabetic drugs on arterial stiffness remains limited. In this study, a network meta‐analysis (NMA) was performed to explore the associations between changes in arterial stiffness and first‐line antidiabetic drugs by evaluating PWV in patients with different metabolic abnormalities.Methods: We systematically searched several electronic databases for randomized controlled trials (RCTs) published from inception until 25 August 2022, without language restrictions. The primary outcome was the change in PWV (ΔPWV) in all included studies; subgroup analysis was performed for patients with abnormal glucose metabolism, including prediabetes and diabetes mellitus. NMA was performed to calculate the mean differences (MDs) with 95% confidence intervals (CIs) as effect sizes to evaluate the ΔPWV.Results: Among the 2257 candidate articles identified in the initial search, 18 RCTs were eventually included in the analysis. In all studies, two classes of new antidiabetic drugs, glucagon‐like peptide‐1 receptor (GLP‐1R) agonists and sSodium‐glucose co‐transporter 2 (SGLT‐2) inhibitors, improved arterial stiffness by decreasing PWV compared with placebo (MD = −1.11, 95% CI: −1.94 to 0.28) and (MD = −0.76, 95% CI: −1.45 to −0.08). A conventional antidiabetic drug, metformin, also showed similar efficacy compared with placebo (MD = −0.73, 95% CI: −1.33 to −0.12). Finally, in subgroup studies of patients with abnormal glucose metabolism diseases, GLP‐1R agonists (MD = −1.06, 95% CI: −2.05 to −0.10) significantly decreased PWV compared with placebo.Conclusion: Three classes of antidiabetic drugs—GLP‐1R agonists, SGLT‐2 inhibitors, and metformin—have the potential to improve arterial stiffness. Among the six classes of antidiabetic drugs analyzed, GLP‐1R agonists constitute the only class of drugs that improves arterial stiffness in patients with abnormal glucose metabolism diseases.

Background. Previous studies have shown that the ratio of triglyceride to high-density lipoprotein cholesterol level (TG/HDL-C) is a risk factor for type 2 diabetes mellitus (T2DM). The aim of this study was to investigate the nonlinear relationship between TG/HDL-C and the incidence of T2DM in a Chinese population. Methods. We used logistic regression models to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the incidence of T2DM among 7,791 participants from the Risk Evaluation of cAncers in Chinese diabeTic Individuals: a lONgitudinal (REACTION) cohort study at baseline. Results. After adjusting for age, sex, body mass index, smoking status, alcohol intake, low-density lipoprotein cholesterol level, strenuous activity, education level, family histories of T2DM and tumors, and the presence of hypertension, tumor, stroke, and coronary heart disease, we showed that TG/HDL-C was positively associated with the incidence of T2DM at the 4-year follow-up ( $\text{OR}=1.49$ , $95\%\text{CI}=1.26–1.78$ ). TG/HDL-C and incidence of T2DM showed a nonlinear relationship; the inflection point of TG/HDL-C was 1.50. The ORs (95% CI) on the left and right sides of the inflection point were 2.50 (1.70–3.67) and 0.96 (0.67–1.37), respectively. After adjusting for age, sex, and body mass index (BMI) in the linear relationship, the OR of the incidence of T2DM was 1.60 ( $95\%\text{CI}=1.37–1.87$ ). When the TG/HDL-C was less than 1.50 or greater than 1.76, the ORs (95% CI) were 2.41 (1.82–3.18) or 0.81 (0.53–1.25), respectively. Subgroup analysis showed no relationships of T2DM incidence with sex, BMI, family history of T2DM, or TG/HDL-C. Conclusion. TG/HDL-C is positively associated with diabetes risk. In our study, with each increasing quintile, the risk of T2DM after 4 years was 1.60 or 1.49 depending on the variables adjusted. In addition, our cohort study showed a nonlinear relationship between TG/HDL-C and T2DM incidence, with an inflection point of 1.76 or 1.50, depending on the variables adjusted. When the TG/HDL was less than 1.50, the ORs (95% CI) were 2.41 (1.82–3.18) and 2.50 (1.70–3.67). When the TG/HDL-C was greater than 1.76 or 1.50, there was no significant difference in the change in OR.

Background: Gout is a chronic disease primarily caused by elevated urate levels, severely affecting joint health. Its global distribution varies, and updated data for China are lacking. This study aimed to analyze the current burden and trends of gout globally and in China, examining the burden by gender, age, and risk factors while providing future predictions. Methods: This descriptive epidemiological secondary analysis utilized data from the Global Burden of Disease, Injuries, and Risk Factors (GBD) 2021 study. Age-standardized incidence rate (ASIR), prevalence rate (ASPR), and disability-adjusted life years (DALYs) rates (ASDR) were used to assess the gout burden. Trends from 1990 to 2021 were analyzed across global regions, genders, and sociodemographic index (SDI) levels. The burden in China was further examined by gender, age, and associated risk factors. The Bayesian age–period–cohort (BAPC) model was used to predict future trends. Gout burden in China and the United States was compared. Results: In 2021, gout affected 57 million people globally, with 9.4 million new cases and 1.75 million DALYs. From 1990 to 2021, the ASIR, ASPR, and ASDR increased by 17.2%, 21.9%, and 21.3%, respectively. Males experienced a significantly higher burden, with greater ASIR, ASPR, and ASDR increasing with higher SDI levels. In China, male ASIR, ASPR, and ASDR were over 2.8 times those of females, and the burden increased with age. In 2021, 31.4% of gout-related DALYs in China were attributed to high body mass index and 7.6% to kidney dysfunction. Between 1990 and 2021, the high body mass index-related burden of gout rose annually for both genders, while the kidney dysfunction-related gout burden remained stable. By 2050, the burden of gout in China is expected to continue increasing, with a slower rise in females and a decline in males after an initial increase. However, the overall burden will remain substantial. In comparison, the gout burden will be higher in the United States than in China. Conclusions: Gout is becoming a significant health burden globally and in China, particularly among Chinese males and older individuals. With the aging population and lifestyle changes exacerbating the issue, effective strategies and measures are essential to prevent or reduce gout-related health issues.