Huachen Jiao

Objective: To investigate factors associated with anxiety, depressive symptoms, and cognitive impairment in individuals with hypertension. Methods: A multicenter, large-sample cross-sectional study was conducted on 1,915 essential hypertension patients from multiple hospitals in Shandong Province (May 2022–July 2024). They were divided into four groups by Mini-Mental State Examination, Hamilton Anxiety and Depression Scales: hypertension alone ( n = 1,350), with cognitive impairment ( n = 191), with anxiety/depression ( n = 309), and with all three conditions ( n = 65). Demographics, clinical indices, lifestyle, sleep quality, and treatment information were collected. Univariate analysis, binary logistic regression, and ROC curves were used to examine these factors. Results: Independent risk factors for hypertension patients with anxiety/depression included waist circumference (OR=1.06), heart rate (1.02), education level, alcohol cessation (3.1), usual systolic blood pressure (1.02) and poor sleep; protective factors included age (0.94), height (0.96), occasional drinking (0.25), hypertension family history (0.15) and lower LDL-C (0.73). For hypertension patients with all three conditions, risk factors were waist circumference (1.07) and poor sleep. Lower LDL-C (0.62) was a protective factor. ROC curves showed good discriminative capacity (AUC=0.895, 0.887). Conclusion: Among individuals with hypertension, comorbid anxiety, depression, and cognitive impairment are associated with poorer sleep quality and elevated waist circumference. Lower LDL-C and appropriate lipid management may have protective effects.

Patients with hypertension commonly experience metabolic dysfunction and cognitive decline. Previous studies have shown that sedentary behavior can affect metabolism. The weight-adjusted waist circumference index (WWI) has become a new indicator of obesity. This study examines the association between sedentary time and hypertension combined with cognitive decline (HCD), with a focus on assessing the mediating role of WWI. A total of 6098 hypertensive patients from May 2022 to July 2024 were included in this study from the hypertension follow-up system. Various statistical techniques such as logistic regression, subgroup analysis, smoothed curve fitting, and causal mediation analysis were used in the study to analyze the information collected from hypertensive patients. In completely adjusted models, there was a noteworthy statistically positive relationship between sedentary time and HCD with an odds ratio (OR) of 3.50 and a 95% confidence interval (CI) of (2.37, 5.16). The causal mediation analysis showed that the relationship between sedentary time and HCD was partially influenced by the mediating effect of WWI with a mediation ratio of 3.6%. Based on this study, sedentary time was significantly and positively associated with the prevalence of HCD, with WWI playing a mediating role. This finding provides a new perspective on the prevention and management of HCD.

Background: There have been sufficient previous studies demonstrating that hyperuricemia (HUA) is closely associated with the occurrence of atrial fibrillation (AF).The incidence of AF in patients with hyperuricemia is higher than that in the general population. Therefore, it is meaningful to explore the serum markers of AF in the HUA population and establish early warning indicators.Objective: To preliminarily explore the correlation between HUA and AF at the metabolomics level, and to identify a group of metabolites with potential predictive power for AF that can be used for further large-scale studies.Methods: This study used untargeted metabolomics technology to detect serum metabolites of patients with AF, patients with AFHUA, and control group. Receiver operator characteristic (ROC) curve were used to analyze differential metabolites.Results: Ultimately, multiple metabolites such as L-Threonine, DL-Malic acid, L-Valine, L-Cysteine were identified as early warning markers of AF in patients with HUA. Combined ROC curve using these four metabolites between the AFHUA/Control comparison group and the AFHUA/AF comparison group showed good predictive efficacy, with Area Under the ROC Curve (AUC) = 0.923 (P < 0.001) in the AFHUA/Control comparison group and AUC = 0.714 (P < 0.001) in the AFHUA/AF comparison group. This provides an early predictive method for patients who may develop atrial fibrillation among those with hyperuricemia. And offers new approaches for the prevention and treatment of atrial fibrillation.Conclusion: This study indicates that serum metabolomics can be specifically used to predict the probability of AF occurrence in individuals with HUA, and has identified metabolites such as L-Threonine, DL-Malic acid, L-Valine, and L-Cysteine that possess potential predictive efficacy.

Machine learning (ML) risk prediction models for post-stroke cognitive impairment (PSCI) are still far from optimal. This study aims to generate a reliable predictive model for predicting PSCI in Chinese individuals using ML algorithms. We collected data on 494 individuals who were diagnosed with acute ischemic stroke (AIS) and hospitalized for this condition from January 2022 to November 2023 at a Chinese medical institution. We assessed cognitive function of patients recently diagnosed with a stroke (in the preceding 3–6 months), PSCI was determined from MMSE or MOCA scores. All of the observed samples were divided into a training set (70%) and a validation set (30%) at random. The least absolute shrinkage and selection operator (LASSO) penalty and logistic regression (LR) can help filter the best predictive features for PSCI from 49 common clinical parameters collected on admission. We utilized seven different ML models, including LR, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Gaussian naive bayes (GNB), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and compared their performance for the resulting variables. We used tenfold cross-validation to measure the model’s AUROC (Area under the receiver operating characteristic), sensitivity, specificity, accuracy, F1 score and AP (Average precision) values. SHAP (Shapley additive exPlanations) analysis provides a comprehensive and detailed explanation of our optimized model’s performance. PSCI was identified in 58.50% of the 494 eligible AIS patients. Age, National institutes of health stroke scale (NIHSS), Hamilton depression scale (HAMD)-24, Pittsburgh sleep quality index (PSQI), ALB, FBG, hypertension, paraventricular lesion, and number of lesions were significant influencing features of PSCI. The AUROC of the XGBoost model is 0.980, which is better than the prediction performance of the other models (LR: 0.808, LightGBM: 0.800, AdaBoost: 0.893, GNB: 0.789, MLP: 0.745, and SVM: 0.868). The XGBoost model, leveraging predictors including age, NIHSS, HAMD-24, PSQI, ALB, FBG, hypertension, paraventricular lesion, and number of lesions, effectively predicts mild to moderate cognitive impairment 3–6 months post-stroke. This tool enables early identification of at-risk patients, facilitating timely clinical interventions.

Background and objective: Risk-based predictive models are a reliable tool for early identification of hypertensive cognitive impairment. However, the evidence of the combination of individual factors and natural environmental factors is still insufficient. The aim of this study was to establish a well-performing machine learning (ML) model based on personal and natural environmental factors to help assess the risk of early cognitive impairment in hypertension.Methods: In this study, a total of 757 Chinese hypertensive patients from from different regions of Shandong Province, China (aged 31–95, male 49.01%) were randomly divided into training group (70%) and verification group (30%). Modelling variables were determined by a 5-fold cross-validated least absolute shrinkage and selection operator (LASSO) regression analysis. Five ML classifiers, XGB (extreme gradient boosting), LR (logistic regression), AdaBoost (adaptive boosting), GNB (gaussian naive bayes), and SVM (support vector machines), have been developed. Area under the ROC curve (AUC), accuracy, sensitivity, specificity, and F1 scores were used to access the model performance. Shape Additive explanation (SHAP) models reveal the feature importance. The clinical performance of the model was evaluated by Decision Curve Analysis (DCA).Results: Cognitive impairment was diagnosed in 17.44% (n = 132). LASSO regression analyses suggested that age, waist circumference, urban green coverage, educational levels, annual sunshine hours, and area whole-day average noise were considered significant predictors of early cognitive impairment in hypertension. The obtained XGBoost model yielded good predictive performance with the AUC (0.893), F1 score (0.627), accuracy (0.837), sensitivity (0.780), and specificity (0.853). The predictive model's clinical net benefit was confirmed through DCA analysis.Conclusion: The XGBoost model developed based on personal factors and natural environmental factors can predict early cognitive impairment of hypertension with superior predictive performance. Larger population cohorts are needed in the future to validate these findings and potentially enhance the ability to identify the occurrence of early cognitive impairment in people with hypertension.

Current evidence for predictive models of post-stroke depression (PSD) risk based on machine learning (ML) remains limited. The aim of this study is to develop a superior predictive model based on ML algorithms for PSD in the Chinese population. We retrospectively gathered data from 507 patients who were hospitalized for ischemic stroke between June 2022 and August 2023 at a medical facility in China. The patients were separated into a training group (70%) and a validation group (30%). After selecting the core predictors of PSD using LASSO regression dimension reduction, six machine learning (ML) algorithms were used to statistically model the risk prediction of PSD. Based on five-fold cross-validation, we evaluated the predictive performance of the developed model. Shape Additive Explanation (SHAP) analysis was then used to interpret the best-performing model. PSD developed in 158 (31.16%) of the 507 eligible patients. Frontal lobe lesion, number of lesions, ALB, NIHSS, PSQI, and MMSE were considered significant predictors of PSD. The AUC(0.941), accuracy (0.876), sensitivity (0.822), specificity (0.899) , F1 score (0.802), and average precision (AP) value (0.858) of XGBoost model were superior to other ML models. The XGBoost model offers an interpretable PSD prediction tool using key clinical indicators, though external validation is needed to confirm generalizability.

Background: As a new obesity-related index, the weight-adjusted waist circumference index (WWI) seems to be a good predictor of cognitive decline in hypertensive patients. This study aimed to verify the relationship between WWI and cognitive decline in Chinese hypertensive patients.Methods: Data were obtained from the Hypertension Follow-up System of Shandong Province. WWI was calculated by dividing waist circumference by the square root of body weight, and cognitive decline was judged based on Mini-Mental State Examination (MMSE) scale scores. Multivariate logistic regression models and subgroup analyses were used to assess the relationship between WWI and cognitive decline in hypertensive patients.Results: A total of 2,204 participants were included. There was a positive association between WWI and cognitive decline in hypertension (HCD). After adjusting for all covariates, a one-unit increase in WWI was associated with a 12% increase in the risk of cognitive decline in hypertensive patients (OR: 1.12, 95%CI: 1.04–1.21). In addition, the multivariable-adjusted OR for the highest quartile (11.16–16.76) compared with the lowest quartile of WWI (7.00–10.11) was 1.61 (95% CI: 1.30–2.00).Conclusion: In Chinese hypertensive patients, high levels of WWI were significantly associated with an increased risk of cognitive decline. This finding suggests that WWI may be an indicator of the risk of cognitive decline affecting hypertensive patients.

Previous studies have shown that lower serum lipid levels are associated with the development of cognitive impairment (CI), dementia, and Alzheimer’s disease. However, the relationship between serum lipid levels and CI in hypertensive patients has not been determined. This case–control study aimed to investigate the relationship between serum lipid levels and CI in hypertensive patients. A total of 1840 hypertensive patients (age: 69.70 ± 6.07; sex: male: 908/49.35%) were enrolled in this study, including 460 hypertensive patients with CI and 1380 hypertensive patients with normal cognitive function matched 1:3 by age and sex. The cognitive function and sleep quality of hypertensive patients were assessed using the Mini-mental State Examination (MMSE) and Pittsburgh Sleep Quality Index (PSQI). The relationship between serum lipid levels and CI in hypertensive patients was analyzed using multifactorial logistic regression. Spearman’s correlation coefficient was used to analyze the correlation of serum lipid levels with MMSE scores and PSQI total scores in hypertensive patients. After adjusting for all factors, serum low-density lipoprotein cholesterol (LDL-C) levels were negatively correlated with CI in hypertensive patients (OR = 0.823, 95%CI: 0.729–0.928, P = 0.001), and this association remained significant in patients with at least a junior high school education (OR = 0.727, 95%CI: 0.592–0.894, P = 0.002). However, serum total cholesterol (TC) and triglyceride (TG) levels were not correlated with CI in patients with hypertension (P > 0.05). In addition, serum LDL-C levels were positively correlated with MMSE total score (r = 0.139, P < 0.001), orientation (r = 0.118, P < 0.001), memory (r = 0.057, P = 0.014), attention and numeracy (r = 0.091, P < 0.001), recall ability (r = 0.065, P = 0.005), and language ability (r = 0.107, P < 0.030); serum TG, TC, and LDL-C levels were negatively correlated with PSQI total score (r = − 0.051, P = 0.029; r = − 0.090, P < 0.001; r = − 0.082, P < 0.001). Lower serum LDL-C levels are associated with CI in hypertensive patients. Although causality cannot be inferred, findings suggest that LDL-C may be a relevant biomarker in cognitive screening. Therefore, serum lipid levels should be reasonably controlled according to their individual conditions.

Background: Previous studies have found that poor sleep quality promotes the occurrence of cognitive impairment (CI), but this relationship has been rarely reported in older adults hypertensive patients. The purpose of this study was to investigate the relationship between sleep quality and CI in older adults hypertensive patients and the mediating effect of sleep quality between physical activity (PA) and CI.Methods: A total of 2072 older adults hypertensive patients were included in this case–control study. Five hundred and eighteen older adults hypertensive patients with CI were matched 1:3 by age and sex to 1,554 older adults hypertensive patients with normal cognitive function. The International Physical Activity Questionnaire-Long Form, Pittsburgh Sleep Quality Index, and Mini-Mental State Examination were used to evaluate PA intensity, sleep quality, and cognitive function in older adults hypertensive patients. Multivariate logistic regression and the mediation package in R Language were used to analyze the relationship between sleep quality and CI and the mediating effect of sleep quality between PA intensity and CI in older adults hypertensive patients.Results: After adjusting for all confounding factors, sleep quality was positively correlated with CI in older adults hypertensive patients (OR = 2.565, 95%CI: 1.958–3.360, p < 0.001), and this relationship also existed in the older adults hypertensive patients with education levels of primary school and below and junior high school and above (OR = 2.468, 95%CI: 1.754–3.473, p < 0.001; OR = 2.385, 95%CI: 1.367–4.161, p = 0.002). In addition, sleep quality mediated part of the mediating effect between PA intensity and CI in older adults hypertensive patients (Za*Zb: - 17.19339; 95%CI: −0.37312, −0.04194).Conclusion: Poor sleep quality was associated with the occurrence of CI in older adults hypertensive patients, and this relationship also existed in older adults hypertensive patients with education levels of primary school and below and junior high school and above.

Previous studies have shown that a higher intensity of physical activity (PA) is associated with a lower risk of cognitive impairment (CI), whereas hypertension is associated with higher CI. However, there are few studies on the association between PA intensity and cognitive function in hypertensive patients. This study investigated the association between PA intensity and cognitive function in hypertensive patients. A total of 2035 hypertensive patients were included in this study, including 407 hypertensive patients with CI and 1628 hypertensive patients with normal cognitive function matched 1:4 by age and sex. The International Physical Activity Questionnaire-Long Form and the Mini-mental State Examination were used to evaluate PA intensity, total metabolic equivalents, and cognitive function in patients with hypertension. Multivariate logistic regression was used to analyze the correlation between PA intensity and CI in hypertensive patients. The Spearman correlation coefficient was used to analyze the correlation between PA intensity and the total score of each component of the MMSE and the correlation between PA total metabolic equivalents and cardiac structure in hypertensive patients. After adjusting for all confounding factors, PA intensity was negatively associated with CI in hypertensive patients (OR = 0.608, 95% CI: 0.447–0.776, P < 0.001), and this association was also observed in hypertensive patients with education level of primary school and below and junior high school and above (OR = 0.732, 95% CI: 0.539–0.995, P = 0.047; OR = 0.412, 95% CI: 0.272–0.626, P < 0.001). The intensity of PA in hypertensive patients was positively correlated with orientation (r = 0.125, P < 0.001), memory (r = 0.052, P = 0.020), attention and numeracy (r = 0.151, P < 0.001), recall ability (r = 0.110, P < 0.001), and language ability (r = 0.144, P < 0.001). PA total metabolic equivalents in hypertensive patients were negatively correlated with RVEDD and LAD (r = − 0.048, P = 0.030; r = − 0.051, P = 0.020) and uncorrelated with LVEDD (r = 0.026, P = 0.233). Higher PA intensity reduced the incidence of CI in hypertensive patients. Therefore, hypertensive patients were advised to moderate their PA according to their circumstances.