The concept of using single criterion of normal blood pressure with systolic blood pressure (SBP) < 140 mmHg and diastolic blood pressure (DBP) < 90 mmHg for all ages is still disputable. The aim of the study is to identify the cutoff value of normotension in different age and sex groups. Totally, 127,922 (63,724 men and 64,198 women) were enrolled for the analysis. Finally, four fifths of them were randomly selected as the study group and the other one fifths as the validation group. Due the tight relationship with comorbidities from cardiovascular disease (CVD), metabolic syndrome (MetS) was used as a surrogate to replace the actual cardiovascular outcomes in the younger subjects. For SBP, MetS predicted by our equation had a sensitivity of 55% and specificity of 67% in males and 65%, 83% in females, respectively. At the same time, they are 61%, 73% in males and 73%, 86% in females for DBP, respectively. These sensitivity, specificity, odds ratio, and area under the receiver operating characteristic curve from our equations are all better than those derived from the criteria of 140/90 or 130/85 mmHg in both genders. By using the presence of MetS as the surrogate of CVD, the regression equations between SBP, DBP, and age were built in both genders. These new criteria are proved to have better sensitivity and specificity for MetS than either 140/90 or 130/85 mmHg. These simple equations should be used in clinical settings for early prevention of CVD.

Objective Although it is known that high uric acid (UA) level is associated with type 2 diabetes (T2DM) and metabolic syndrome (MetS), most of the previous studies were focused on adults. Since aging becomes a major problem for many societies, in this longitudinal study, we investigated the role of UA in future T2DM and MetS in a large cohort of people who were older than 65 years. Design A cross-sectional and longitudinal study. Setting/Participants 18,907 elderly (9,732 men, 9,175 women) aged above 65 years, enrolled from health check-up centers, were classified into three subgroups by 10-year intervals (young old 65-74 years, YO; old old 75-84 years, OO; and oldest old 85-94 years, ODO), with the average follow-up period of 4.3 years. Measurements The optimal cut-off values (CoVs) of baseline UA to predict future MetS and T2DM were determined by receiving operating characteristic (ROC) curve analysis. Using these CoVs of UA, the participants were divided into normal- and high-level groups of UA. Cox proportional hazard analysis was used to calculate hazard ratios (HRs) for the subjects with a high level of UA for the risk of future MetS and T2DM. In addition, Kaplan-Meier plots and log rank test were used to evaluate the time effect on the incidence of developing MetS and T2DM between the two groups. Results In ROC curve analysis, the optimal CoVs of baseline UA were 6.0, 6.3 and 6.7 mg/dl in YO, OO, and ODO men, respectively; 5.5 and 4.9 mg/dl in YO and OO women, respectively (all p < 0.05). However, the CoVs of UA in ODO women (6.1 mg/dl) failed to show its discriminant power (p = 0.13). The Cox regression analysis showed the YO subjects with a higher baseline level of UA had a higher risk of developing MetS (HRs 1.56 and 1.58 for men and women, respectively, both p < 0.001); as for T2DM the HRs were 1.39 and 1.57. In OO men, the HRs was 1.89 for developing future MetS. However, no significant findings could be noted in the ODO group. Kaplan-Meier plots and log rank test also showed the same findings. Conclusion Our study showed that old subjects with high levels of UA will have a higher chance to have MetS and T2DM, particularly in the YO group (6.0 mg/dl for men and 5.5 mg/dl for women, respectively). Using UA as one of the metabolic biomarkers may help clinicians to early detect and prevent MetS and diabetes.

Carotid intima-media thickness (c-IMT) is a reliable risk factor for cardiovascular disease risk in type 2 diabetes (T2D) patients. The present study aimed to compare the effectiveness of different machine learning methods and traditional multiple logistic regression in predicting c-IMT using baseline features and to establish the most significant risk factors in a T2D cohort. We followed up with 924 patients with T2D for four years, with 75% of the participants used for model development. Machine learning methods, including classification and regression tree, random forest, eXtreme gradient boosting, and Naïve Bayes classifier, were used to predict c-IMT. The results showed that all machine learning methods, except for classification and regression tree, were not inferior to multiple logistic regression in predicting c-IMT in terms of higher area under receiver operation curve. The most significant risk factors for c-IMT were age, sex, creatinine, body mass index, diastolic blood pressure, and duration of diabetes, sequentially. Conclusively, machine learning methods could improve the prediction of c-IMT in T2D patients compared to conventional logistic regression models. This could have crucial implications for the early identification and management of cardiovascular disease in T2D patients.

The urine albumin–creatinine ratio (uACR) is a warning for the deterioration of renal function in type 2 diabetes (T2D). The early detection of ACR has become an important issue. Multiple linear regression (MLR) has traditionally been used to explore the relationships between risk factors and endpoints. Recently, machine learning (ML) methods have been widely applied in medicine. In the present study, four ML methods were used to predict the uACR in a T2D cohort. We hypothesized that (1) ML outperforms traditional MLR and (2) different ranks of the importance of the risk factors will be obtained. A total of 1147 patients with T2D were followed up for four years. MLR, classification and regression tree, random forest, stochastic gradient boosting, and eXtreme gradient boosting methods were used. Our findings show that the prediction errors of the ML methods are smaller than those of MLR, which indicates that ML is more accurate. The first six most important factors were baseline creatinine level, systolic and diastolic blood pressure, glycated hemoglobin, and fasting plasma glucose. In conclusion, ML might be more accurate in predicting uACR in a T2D cohort than the traditional MLR, and the baseline creatinine level is the most important predictor, which is followed by systolic and diastolic blood pressure, glycated hemoglobin, and fasting plasma glucose in Chinese patients with T2D.