To clarify the association of sleep duration with all-cause and cardiovascular mortality, and further estimate the population attributable fraction (PAF) for the 10-year risk of cardiovascular disease (CVD) due to inappropriate sleep duration among US adults, we included data of the National Health and Nutrition Examination Survey (NHANES) from 2005 to 2014 by linkage to the National Death Index until December 31, 2015 in a prospective design. Cox proportional hazards models were used for multivariate longitudinal analyses. The Pooled Cohort Equations methods was adopted to calculate the predicted 10-year CVD risk. In the current study, sleep <5 h or longer than 9 h per day were significantly associated with elevated risks of all-cause mortality, and the multivariable-adjusted HRs across categories were 1.40 (95% CI, 1.14–1.71), 1.12 (95% CI, 0.91–1.38), 1 (reference), 1.35 (95% CI, 1.12–1.63), and 1.74 (95% CI, 1.42–2.12). Similarly, the HRs of cardiovascular mortality across categories were 1.66 (95% CI, 1.02–2.72), 1.15 (95% CI, 0.77–1.73), 1 (reference), 1.55 (95% CI, 1.05–2.29), and 1.81 (95% CI, 1.09–3.02). Under a causal–effect assumption, we estimated that 187 000 CVD events (PAF 1.8%, 0.9% to 2.3%) were attributable to short sleep duration and 947 000 CVD events (PAF 9.2%, 6.4% to 11.6%) were attributable to long sleep duration from 2018 to 2028. This study informed the potential benefit of optimizing the sleep duration for the primary prevention of CVD in a contemporary population.

Early identification of individuals at high risk of diabetes is crucial for implementing early intervention strategies. However, algorithms specific to elderly Chinese adults are lacking. The aim of this study is to build effective prediction models based on machine learning (ML) for the risk of type 2 diabetes mellitus (T2DM) in Chinese elderly. A retrospective cohort study was conducted using the health screening data of adults older than 65 years in Wuhan, China from 2018 to 2020. With a strict data filtration, 127,031 records from the eligible participants were utilized. Overall, 8298 participants were diagnosed with incident T2DM during the 2-year follow-up (2019–2020). The dataset was randomly split into training set (n = 101,625) and test set (n = 25,406). We developed prediction models based on four ML algorithms: logistic regression (LR), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost). Using LASSO regression, 21 prediction features were selected. The Random under-sampling (RUS) was applied to address the class imbalance, and the Shapley Additive Explanations (SHAP) was used to calculate and visualize feature importance. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. The XGBoost model achieved the best performance (AUC = 0.7805, sensitivity = 0.6452, specificity = 0.7577, accuracy = 0.7503). Fasting plasma glucose (FPG), education, exercise, gender, and waist circumference (WC) were the top five important predictors. This study showed that XGBoost model can be applied to screen individuals at high risk of T2DM in the early phrase, which has the strong potential for intelligent prevention and control of diabetes. The key features could also be useful for developing targeted diabetes prevention interventions.

Identifying people with a high risk of developing diabetes among those with prediabetes may facilitate the implementation of a targeted lifestyle and pharmacological interventions. We aimed to establish machine learning models based on demographic and clinical characteristics to predict the risk of incident diabetes. We used data from the free medical examination service project for elderly people who were 65 years or older to develop logistic regression (LR), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) machine learning models for the follow-up results of 2019 and 2020 and performed internal validation. The receiver operating characteristic (ROC), sensitivity, specificity, accuracy, and F1 score were used to select the model with better performance. The average annual progression rate to diabetes in prediabetic elderly people was 14.21%. Each model was trained using eight features and one outcome variable from 9607 prediabetic individuals, and the performance of the models was assessed in 2402 prediabetes patients. The predictive ability of four models in the first year was better than in the second year. The XGBoost model performed relatively efficiently (ROC: 0.6742 for 2019 and 0.6707 for 2020). We established and compared four machine learning models to predict the risk of progression from prediabetes to diabetes. Although there was little difference in the performance of the four models, the XGBoost model had a relatively good ROC value, which might perform well in future exploration in this field.

Background: the epidemiological characteristics of older patients with COVID-19 was far from clear. Objective: to explore the epidemiology of older patients with COVID-19 in Wuhan, China. Design: a retrospective cross-sectional study. Setting: a population-based study. Subjects: the resident older patients (>65 years) diagnosed with COVID-19. Methods: city-wide case series reported to Wuhan Center for Disease Control and Prevention from 12 December 2019 to 17 March 2020 were included. The epidemic curves were constructed by dates of disease onset. Results: 14,238 confirmed COVID-19 cases were older persons. The number of male cases were slightly less than female cases (1:1.01). The attack rate of COVID-19 in the older persons was 11.49‰ in Wuhan. There was a rapid increase of disease at the early stage of the epidemic and then a gradual and steady decrease was performed. 3,723 (26.15%) and 734 (5.16%) patients were diagnosed as severe and critical cases, respectively. The attributable crude fatality ratio of COVID-19 in the older population was 222.57/100,000, and the crude fatality ratio of COVID was 19.37%. The proportion of severe and critical cases, and fatality ratio were both higher in downtown area and increased with age. Conclusions: the older persons are sensitive to COVID-19. The proportion of severe and critical cases and fatality ratio are higher than that in children and younger adults. Strengthen the protection and control strategies for the older adults are of priorities. More detailed epidemiological and clinical information should be measured in further studies.

Epidemiological evidence linking type 2 diabetes mellitus (T2DM) with air pollution is discrepant and most are restricted to the influences of air-pollutant mass concentration. This study aims to explore the effects of long-term exposure to air pollution and its metal constituents on T2DM prevalence in China. We used data on 10,253 adult residents from the baseline survey of Wuhan Chronic Disease Cohort in 2019. Ambient PM_2.5, PM₁₀ and NO₂ exposure were estimated at residences based on Chinese Air Quality Reanalysis Dataset. Concentrations of 10 metal constituents were measured by 976 PM_2.5 filter samples collected from four monitoring stations. Logistic regression models were employed to examine associations of T2DM prevalence with 3-year mean concentrations of each air pollutant and PM_2.5 metal constituents prior to the baseline investigation. A total of 673 T2DM cases (6.6%) were identified. The 3-year mean exposures to PM_2.5, PM₁₀ and NO₂ were 50.89 μg/m³, 82.86 μg/m³, and 39.79 μg/m³, respectively. And interquartile range (IQR) of 10 metals in PM_2.5 varied from 0.03 ng/m³ to 78.30 ng/m³. For 1 μg/m³ increment in PM_2.5, PM₁₀ and NO₂, the odds of T2DM increased by 7.2% (95%CI: 1.026, 1.136), 3.1% (95%CI: 1.013, 1.050), and 2.1% (95%CI: 1.005, 1.038) after adjusting for potential confounders. Cd and Sb in PM_2.5 were significant risk factors to T2DM with odds ratios of 1.350 (95%CI: 1.089, 1.673) and 1.389 (95%CI: 1.164, 1.658) for per IQR increase, respectively. Stratification analyses indicated that males and those aged ≥45 years were more susceptive to long-term air pollution. Long-term exposure to PM_2.5, PM₁₀ and NO₂ increased T2DM prevalence in a Wuhan population, especially for men and middle-aged and elderly people. Moreover, T2DM was significantly associated with Cd and Sb in PM_2.5. Further research to validate these results and to clarify the underlying mechanisms is warranted.