A risk prediction model based on machine learning for early cognitive impairment in hypertension: Development and validation study

Neurovascular coupling, functional connectivity, and cerebrovascular endothelial extracellular vesicles as biomarkers of mild cognitive impairment

INTRODUCTION

Mild cognitive impairment (MCI) is a prodromal stage of dementia. Understanding the mechanistic changes from healthy aging to MCI is critical for comprehending disease progression and enabling preventative intervention.

METHODS

Patients with MCI and age-matched controls (CN) were administered cognitive tasks during functional near-infrared spectroscopy (fNIRS) recording, and changes in plasma levels of extracellular vesicles (EVs) were assessed using small-particle flow cytometry.

RESULTS

Neurovascular coupling (NVC) and functional connectivity (FC) were decreased in MCI compared to CN, prominently in the left-dorsolateral prefrontal cortex (LDLPFC). We observed an increased ratio of cerebrovascular endothelial EVs (CEEVs) to total endothelial EVs in patients with MCI compared to CN, correlating with structural MRI small vessel ischemic damage in MCI. LDLPFC NVC, CEEV ratio, and LDLPFC FC had the highest feature importance in the random Forest group classification.

DISCUSSION

NVC, CEEVs, and FC predict MCI diagnosis, indicating their potential as markers for MCI cerebrovascular pathology.

HIGHLIGHTS

Neurovascular coupling (NVC) is impaired in mild cognitive impairment (MCI). Functional connectivity (FC) compensation mechanism is lost in MCI. Cerebrovascular endothelial extracellular vesicles (CEEVs) are increased in MCI. CEEV load strongly associates with cerebral small vessel ischemic lesions in MCI. NVC, CEEVs, and FC predict MCI diagnosis over demographic and comorbidity factors.

Predictive Value of the Total Bilirubin and CA50 Screened Based on Machine Learning for Recurrence of Bladder Cancer Patients

Purpose

Recurrence is the main factor for poor prognosis of bladder cancer. Therefore, it is necessary to develop new biomarkers to predict the prognosis of bladder cancer. In this study, we used machine learning (ML) methods based on a variety of clinical variables to screen prognostic biomarkers of bladder cancer.

Patients and Methods

A total of 345 bladder cancer patients were participated in this retrospective study and randomly divided into training and testing group. We used five supervised clustering ML algorithms: decision tree (DT), random forest (RF), adaptive boosting (AdaBoost), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) to obtained prediction information through 34 clinical parameters.

Results

By comparing five ML algorithms, we found that total bilirubin (TBIL) and CA50 had the best performance in predicting the recurrence of bladder cancer. In addition, the combined predictive performance of the two is superior to the performance of any single indicator prediction.

Conclusion

ML technology can evaluate the recurrence of bladder cancer. This study shows that the combination of TBIL and CA50 can improve the prognosis prediction of bladder cancer recurrence, which can help clinicians make decisions and develop personalized treatment strategies.

Association between intensity of physical activity and cognitive function in hypertensive patients: a case-control study

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.

A non-linear relationship between blood pressure and mild cognitive impairment in elderly individuals: A cohort study based on the Chinese longitudinal healthy longevity survey (CLHLS)

BACKGROUND

Hypertension is an established risk factor for mild cognitive impairment (MCI) in elderly individuals. Nevertheless, the impact of different levels of blood pressure on the progression of MCI remains uncertain. This study aims to investigate the non-linear relationship between blood pressure and MCI in the elderly and detect the critical blood pressure threshold, thus, improving blood pressure management for individuals at high risk of MCI.

METHODS

Data was obtained from the Chinese Longitudinal Healthy Longevity Survey (CLHLS) cohort. We chose normal cognitive elderly individuals who entered the cohort in 2014 for a 5-year follow-up to observe the progression of MCI. Subsequently, we utilized the Cox regression model to identify risk factors for MCI and conducted a Cox-based restricted cubic spline regression (RCS) model to examine the non-linear relationship between systolic blood pressure (SBP) and diastolic blood pressure (DBP) with MCI, determining the critical blood pressure threshold for MCI progression.

RESULTS

In the elderly population, female (HR = 1.489, 95% CI: 1.017-2.180), lacking of exercise in the past (HR = 1.714, 95% CI: 1.108-2.653), preferring animal fats (HR = 2.340, 95% CI: 1.348-4.061), increased age (HR = 1.061, 95% CI: 1.038-1.084), increased SBP (HR = 1.036, 95% CI: 1.024-1.048), and increased DBP (HR = 1.056, 95% CI: 1.031-1.081) were associated with MCI progression. After adjusting factors such as gender, exercise, preferred types of fats, and age, both SBP (P non-linear < 0.001) and DBP (P non-linear < 0.001) in elderly individuals exhibited a non-linear association with MCI. The risk of MCI rose when SBP exceeded 135 mmHg and DBP was in the range of 80-88 mmHg. However, when DBP exceeded 88 mmHg, there was a declining trend in MCI progression, although the HR remained above 1. The identified critical blood pressure management threshold for MCI was 135/80 mmHg.

CONCLUSION

In this study, we discovered that risk factors affecting the progression of MCI in elderly individuals comprise gender (female), preferring to use animal fat, lack of exercise in the past, increased age, increased SBP, and increased DBP. Additionally, a non-linear relationship between blood pressure levels and MCI progression was confirmed, with the critical blood pressure management threshold for MCI onset falling within the prehypertensive range.

Higher remnant cholesterol is associated with an increased risk of amnestic mild cognitive impairment: a community-based cross-sectional study

Background and aims

Amnestic mild cognitive impairment (aMCI) is the most common subtype of MCI, which carries a significantly high risk of transitioning to Alzheimer's disease. Recently, increasing attention has been given to remnant cholesterol (RC), a non-traditional and previously overlooked risk factor. The aim of this study was to explore the association between plasma RC levels and aMCI.

Methods

Data were obtained from Brain Health Cognitive Management Team in Wuhan (https://hbtcm.66nao.com/admin/). A total of 1,007 community-dwelling elders were recruited for this project. Based on ten tools including general demographic data, cognitive screening and some exclusion scales, these participants were divided into the aMCI (n = 401) and normal cognitive groups (n = 606). Physical examinations were conducted on all participants, with clinical indicators such as blood pressure, blood sugar, and blood lipids collected.

Results

The aMCI group had significantly higher RC levels compared to the normal cognitive group (0.64 ± 0.431 vs. 0.52 ± 0.447 mmol/L, p < 0.05). Binary logistics regression revealed that occupation (P<0.001, OR = 0.533, 95%CI: 0.423-0.673) and RC (p = 0.014, OR = 1.477, 95% CI:1.081-2.018) were associated factors for aMCI. Partial correlation analysis, after controlling for occupation, showed a significant negative correlation between RC levels and MoCA scores (r = 0.059, p = 0.046), as well as Naming scores (r = 0.070, p = 0.026). ROC curve analysis demonstrated that RC levels had an independent predictive efficacy in predicting aMCI (AUC = 0.580, 95%CI: 0.544 ~ 0.615, P < 0.001).

Conclusion

Higher RC levels were identified as an independent indicator for aMCI, particularly in the naming cognitive domain among older individuals. Further longitudinal studies are necessary to validate the predictive efficacy of RC.

Application of machine learning in measurement of ageing and geriatric diseases: a systematic review

BACKGROUND

As the ageing population continues to grow in many countries, the prevalence of geriatric diseases is on the rise. In response, healthcare providers are exploring novel methods to enhance the quality of life for the elderly. Over the last decade, there has been a remarkable surge in the use of machine learning in geriatric diseases and care. Machine learning has emerged as a promising tool for the diagnosis, treatment, and management of these conditions. Hence, our study aims to find out the present state of research in geriatrics and the application of machine learning methods in this area.

METHODS

This systematic review followed Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and focused on healthy ageing in individuals aged 45 and above, with a specific emphasis on the diseases that commonly occur during this process. The study mainly focused on three areas, that are machine learning, the geriatric population, and diseases. Peer-reviewed articles were searched in the PubMed and Scopus databases with inclusion criteria of population above 45 years, must have used machine learning methods, and availability of full text. To assess the quality of the studies, Joanna Briggs Institute's (JBI) critical appraisal tool was used.

RESULTS

A total of 70 papers were selected from the 120 identified papers after going through title screening, abstract screening, and reference search. Limited research is available on predicting biological or brain age using deep learning and different supervised machine learning methods. Neurodegenerative disorders were found to be the most researched disease, in which Alzheimer's disease was focused the most. Among non-communicable diseases, diabetes mellitus, hypertension, cancer, kidney diseases, and cardiovascular diseases were included, and other rare diseases like oral health-related diseases and bone diseases were also explored in some papers. In terms of the application of machine learning, risk prediction was the most common approach. Half of the studies have used supervised machine learning algorithms, among which logistic regression, random forest, XG Boost were frequently used methods. These machine learning methods were applied to a variety of datasets including population-based surveys, hospital records, and digitally traced data.

CONCLUSION

The review identified a wide range of studies that employed machine learning algorithms to analyse various diseases and datasets. While the application of machine learning in geriatrics and care has been well-explored, there is still room for future development, particularly in validating models across diverse populations and utilizing personalized digital datasets for customized patient-centric care in older populations. Further, we suggest a scope of Machine Learning in generating comparable ageing indices such as successful ageing index.

Increased extracellular water/body mass is associated with functional impairment in hemodialysis patients

BACKGROUND

Functional impairment, malnutrition and fluid overload are prevalent in patients undergoing maintenance hemodialysis (MHD). The extracellular water/body cell mass ratio (ECW/BCM) is a new indicator reflecting fluid overload and malnutrition. A previous study has suggested that it performs better than other indices in assessing fluid status. This study investigates the relationship between pre-dialysis whole-body ECW/BCM and physical function in MHD patients.

METHODS

We conducted a multicenter, cross-sectional study in Guizhou Province in Southwest China. The Karnofsky Performance Status (KPS) was used to evaluate patients' functional status. Patients with KPS scores of ≤ 80 were considered to have a functional impairment. The body composition was measured using the body composition monitor (BCM), and the value of the ECW/BCM ratio was calculated. The subjects were classified into three groups according to ECW/BCM tertiles. Multiple logistic regression models and interactive analyses were conducted.

RESULTS

The final analysis included 2818 subjects. Multivariate logistic regression analyses showed that compared with the lowest tertile (tertile 1), the adjusted odds ratio of functional impairment were 1.95 (95% CI: 1.21-3.13, p < 0.001) and 2.10 (95% CI: 1.31-3.37, p < 0.001) in the second and the third tertiles of ECW/BCM, respectively after adjusting for age, sex, current smoking status, history of stroke, heart failure, diabetes, and myocardial infarction. Subgroup analysis showed that the association existed stably across all subgroups stratified by age, gender, cognitive impairment (CI), history of stroke, heart failure, and diabetes (all p values for interaction >0.05).

CONCLUSIONS

Elevated ECW/BCM is independently linked to an increased risk of functional impairment in patients with MHD.