Depression is of increasing concern as its prevalence increases. Our study’s objective was to create and evaluate a nomogram to predict the likelihood that hypertension patients may experience depression. 13293 people with hypertension who were under 20 years old were chosen from the National Health and Nutrition Examination Survey (NHANES) database between 2007 and 2018 for this study. The training and validation sets were split up into the dataset at random in a 7:3 ratio. To find independent predictors, univariate and multivariate logistic regression were employed on the training set. Using information from the validation set, nomogram was subsequently created and internally validated. The effectiveness of the nomogram is assessed using calibration curve and receiver operator characteristic (ROC) curve. Combining univariate logistic regression analysis and multifactor logistic regression analysis, the results showed that age, sex, race, marital, education level, sleep time on workdays, poverty to income ratio, smoking, alcohol consumption, sedentary time and heart failure status were risk factors for hypertensive patients suffering from depression and were included in the nomogram model, and ROC analysis showed that the AUC of the training set was 0.757 (0.797–0.586), with a sensitivity of 0.586; the AUC of the test set was 0.724 (0.712–0.626), with a sensitivity of 0.626, which was a good fit. Decision curve analysis further confirms the value of nomogram for clinical application. In the civilian non-institutionalized population of the United States, our study suggests a nomogram that can aid in predicting the likelihood of depression in hypertension patients and aiding in the selection of the most effective treatments.

Background Few epidemiological research has been conducted in hypertensive populations on depression and sleep time on workdays. The aim of our study was to examine the relationship between sleep time on workdays and depression in hypertensive populations from the National Health and Nutrition Examination Survey (NHANES).Methods In all, 9407 individuals from the National Health and Nutrition Examination Survey 2007–2018 with a history of hypertension were examined. We investigated the association between sleep time on workdays and the prevalence of depression in a hypertensive population using weighted univariate logistic regression analysis, weighted multivariate logistic regression analysis, weighted subgroup analysis, and weighted restricted cubic spline analysis.Results Sleep time on workdays was significantly linked with depression in a multivariable logistic regression model that adjusted for all covariates (OR: 0.84, 95% CI: 0.77–0.92, P < 0.01). Additionally, grouping sleep time on workdays into quartiles (Q) revealed a link between reduced workday sleep duration and a higher risk of depression [Q1=(OR:1.00), Q2= (OR:0.50, 95% CI:0.38–0.67, P < 0.01), Q3= (OR:0.51,95% CI:0.38–0.67, P < 0.01), Q3= (OR:0.79, 95% CI:0.57–1.11, P = 0.17)]. We also conducted subgroup analyses for age, gender, race, education, marital status, use of tobacco and alcohol, and other health issues, and discovered moderating effects for sleep time on workdays and depression across these variables(P < 0.05). Finally, we used a weighted restricted cubic spline curve to investigate the non-linear association between sleep time on workdays and depression. We discovered a U-shaped relationship with an inflection point of 7.427. By further stratifying by gender, race, and marital status, we found a non-linear relationship between sleep time on workdays and depression.Conclusion Our results indicate that less sleep time on workdays is associated with an increased risk of depression in people with hypertension.

BackgroundThe purpose of this study was to develop and validate a machine learning (ML) based prediction model for the risk of heart failure (HF) in patients with prediabetes or diabetes.MethodsWe used 3527 subjects aged 40 years and older with a prior diagnosis of prediabetes or diabetes from the National Health and Nutrition Examination Survey (NHANES) from 2007 to 2018. The search for independent risk variables linked to HF was conducted using univariate and multivariable logistic regression analysis. The 3527 subjects were randomly divided into training set and validation set in a 7:3 ratio. Five ML models were built on the training set using five ML algorithms, including random forest (RF), and then validated on the validation set. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis and Bootstrap resampling method were used to measure the predictive performance of the five ML models.ResultsMultivariate logistic regression analysis showed that age, poverty‐to‐income ratio, myocardial infarction condition, coronary heart disease condition, chest pain condition, and glucose‐lowering medication use were independent predictors of HF. By comparing the performance of the five ML models, the RF model (AUC = 0.978) was the best prediction model.ConclusionsThe risk of HF in middle‐aged and elderly patients with prediabetes or diabetes can be accurately predicted using ML models. The best prediction performance is presented by RF model, which can assist doctors in making clinical decisions.