Background: Osteoporosis is becoming more common worldwide, imposing a substantial burden on individuals and society. The onset of osteoporosis is subtle, early detection is challenging, and population-wide screening is infeasible. Thus, there is a need to develop a method to identify those at high risk for osteoporosis.
Objective: This study aimed to develop a machine learning algorithm to effectively identify people with low bone density, using readily available demographic and blood biochemical data.
Methods: Using NHANES 2017–2020 data, participants over 50 years old with complete femoral neck BMD data were selected. This cohort was randomly divided into training (70%) and test (30%) sets. Lasso regression selected variables for inclusion in six machine learning models built on the training data: logistic regression (LR), support vector machine (SVM), gradient boosting machine (GBM), naive Bayes (NB), artificial neural network (ANN) and random forest (RF). NHANES data from the 2013–2014 cycle was used as an external validation set input into the models to verify their generalizability. Model discrimination was assessed via AUC, accuracy, sensitivity, specificity, precision and F1 score. Calibration curves evaluated goodness-of-fit. Decision curves determined clinical utility. The SHAP framework analyzed variable importance.
Results: A total of 3,545 participants were included in the internal validation set of this study, of whom 1870 had normal bone density and 1,675 had low bone density Lasso regression selected 19 variables. In the test set, AUC was 0.785 (LR), 0.780 (SVM), 0.775 (GBM), 0.729 (NB), 0.771 (ANN), and 0.768 (RF). The LR model has the best discrimination and a better calibration curve fit, the best clinical net benefit for the decision curve, and it also reflects good predictive power in the external validation dataset The top variables in the LR model were: age, BMI, gender, creatine phosphokinase, total cholesterol and alkaline phosphatase.
Conclusion: The machine learning model demonstrated effective classification of low BMD using blood biomarkers. This could aid clinical decision making for osteoporosis prevention and management.
Background: With the rapid growth of global aging, frailty has become a serious public health burden, affecting the life quality of older adults. Depressive symptoms (depression hereafter) and sleep quality are associated with frailty, but the pathways in which sleep quality and depression affect frailty remain unclear.
Method: This cross-sectional study included 1866 community-dwelling older adults. Demographic characteristics and health-related data of them was collected, and we also assessed frailty, depression, and sleep quality. Descriptive statistics were carried out and ordinal logistic regression analysis was used to identify the factors correlated with frailty. Spearman correlation analysis and mediation analysis were employed to assess associations between sleep quality, depression and frailty. Two-sided p < 0.05 was considered as significant.
Results: The results showed that 4.1% older adults were frail and 31.0% were pre-frail. Ordinal logistic regression showed that age, consumptions of vegetables, exercise, sleep quality, depression, number of chronic diseases, chronic pain, and self-rated health were correlated with frailty. Spearman correlation analysis revealed that frailty was associated with depression and sleep quality. There was a mediation effect that sleep quality was a significant and positive predictor of frailty (total effect = 0.0545, 95% boot CI = 0.0449–0.0641), and depression was a mediator between sleep quality and frailty (mediation effect = 60.4%).
Conclusion: Depression and poor sleep quality may be early indicators of frailty in older adults. Improving the sleep quality and psychological state of older adults can improve frailty, which is beneficial for healthy aging.
Objective: This review aimed to analyze and compare the accuracy of eight screening tools for sarcopenia in older Chinese adults according to different diagnostic criteria.
Methods: This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The PubMed, Embase, Web of Science, China National Knowledge Infrastructure (CNKI), and Wanfang databases were searched between the publication of the first expert consensus on sarcopenia in 2010 and April 2023 using relevant MeSH terms. We evaluated the risk bias of the included studies using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. The pooled result of sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and plot the summary receiver operating characteristic curve (SROC) were calculated by using a bivariate random-effects model. The accuracies of sensitivity and specificity of the screening tools were compared using the Z-test.
Results: A total of 30 studies (23,193 participants) were included, except for calf circumference (CC), Ishii, and Finger-ring Test; Screening tools for sarcopenia in older Chinese adults have consistently shown low to moderate sensitivity and moderate to high specificity. Regional and sex differences affect the accuracy of the screening tools. In terms of sensitivity and specificity, the CC, Ishii, and Finger-ring Test were superior to the other screening tools.
Conclusion: The Asian Working Group on Sarcopenia (AWGS) 2019 criteria are more appropriate for the diagnosis of sarcopenia in older Chinese adults. According to the AWGS 2019, CC and Ishii are recommended for sarcopenia screening in older Chinese adults.
Introduction: Tooth loss is associated with increased mortality risk; however, the mechanism underlying this is still not clear. The objective of this study was to explore whether frailty mediates the association between tooth loss and mortality risk among the oldest old individuals.
Methods: The participants were followed up from 1998 to 2018 in the Chinese Longitudinal Healthy Longevity Survey (CLHLS). Frailty was constructed following a standard procedure. Mortality, frailty, and tooth loss were applied as the outcome, mediator, and independent variables, respectively. The Cox model was fitted, including possible confounders, for causal mediation analysis. A total effect (TE), an average causal mediation effect (ACME), an average direct effect (ADE), and a proportion mediated (PM) effect were calculated.
Results: During the 129,936 person-years at risk, 31,899 individuals with a mean age of 91.79 years were included. The TE and ADE of severe tooth loss on mortality were 0.12 (95% CI: 0.08, 0.15) and 0.09 (95% CI: 0.05, 0.13); the ACME of frailty was 0.03 (95% CI: 0.02, 0.03) with 21.56% of the TE being mediated.
Discussion: This study illustrated that tooth loss is associated with mortality, and frailty appeared to mediate the relationship. It is recommended that oral health indicators and frailty status be incorporated into routine geriatric assessments to promote optimal oral health and non-frailty status.