Prevalence and Risk Factors of Stroke in Inpatients with Type 2 Diabetes Mellitus in China

Objective The prevalence and the cluster characteristics of risk factors of stroke were assessed in a Chinese diabetic population.Methods Clinical data of 30693 inpatients who were diagnosed with type 2 diabetes mellitus(T2DM)and admitted between 2013 and 2018 were retrospectively analyzed.The age-standardized prevalence of stroke was estimated using the 2010 Chinese population census data,and risk factors were analyzed by multiple imputation and regression.Results The crude and standardized prevalence rates of stroke in patients with T2DM were 34.4%and 21.5%,respectively,and 85.2%of the stroke patients had ischemic stroke.Nearly half of the patients who experienced stroke had clusters of more than 4 risk factors.Compared with no-risk-factor clustering,the risk of stroke significantly increased 3-4 times in the presence of more than 4 risk-factor clusters(P<0.001).Hypertension was the most common major risk factor for ischemic stroke[odds ratio(OR),2.34;95%confidence interval(CI),2.18-2.50]and hemorrhagic stroke(OR,3.68;95%CI 2.95-4.59;P<0.001).Moreover,a 1-standard-deviation increase in fasting blood glucose(FBG)was significantly negatively correlated with ischemic stroke risk,and the same change in FBG was significantly associated with an 8%increased risk of hemorrhagic stroke.Conclusion The prevalence of stroke in patients with T2DM is rather high,and the clustering of risk factors is associated with the development of stroke in T2DM patients.Risk factors differ in different stroke subtypes.Identifying risk factors for a specific high-risk group is necessary.

Performance of Fasting Plasma Glucose and Postprandial Urine Glucose in Screening for Diabetes in Chinese High-risk Population

Background： The conventional approaches to diabetes screening are potentially limited by poor compliance and laboratory demand. This study aimed to evaluate the performance of fasting plasma glucose （FPG） and postprandial urine glucose （PUG） in screening for diabetes in Chinese high-risk population. Methods： Nine hundred and nine subjects with high-risk factors of diabetes underwent oral glucose tolerance test after an overnight fast. FPG, hemoglobin A 1 c, 2-h plasma glucose （2 h-PG）, and 2 h-PUG were evaluated. Diabetes and prediabetes were defined by the American Diabetes Association criteria. The area under the receiver operating characteristic （ROC） curve was used to evaluate the diagnostic accuracy of 2 h-PUG, and the optimal cut-off determined to provide the largest Youden index. Spearman correlation was used for relationship analysis. Results： Among 909 subjects, 33.4% （304/909） of subjects had prediabetes, and 17.2% （156/909） had diabetes. The 2 h-PUG was positively related to FPG and 2 h-PG （r = 0.428 and 0.551, respectively, both P 〈 0.001）. For estimation of 2 h-PG 〉 7.8 mmol/L and 2 h-PG ≥ 11.I mmol/L using 2 h-PUG, the area under the ROC curve were 0.772 （95% confidence interval [CI]： 0.738-0.806） and 0.885 （95% CI：0.850-0.921 ）, respectively. The corresponding optimal cut-offs for 2 h-PUG were 5.6 mmol/L and 7.5 retool/L, respectively. Compared with FPG alone, FPG combined with 2 h-PUG had a higher sensitivity fbr detecting glucose abnormalities （84.1% vs. 73.7%, P〈 0.001） and diabetes （82.7% vs. 48.1%, P〈 0.001）. Conclusion： FPG combined with 2 h-PUG substantially improves the sensitivity in detecting prediabetes and diabetes relative to FPG alone, and may represent an efficient layperson-oriented diabetes screening method.