Association between liver enzymes and bone mineral density in Koreans: a cross-sectional study

Development and validation of explainable machine learning models for female hip osteoporosis using electronic health records

BACKGROUND

Hip fractures are associated with reduced mobility, and higher morbidity, mortality, and healthcare costs. Approximately 90% of hip fractures in the elderly are associated with osteoporosis, making it particularly important to screen the population for hip osteoporosis and intervene early. Dual-energy X-ray absorptiometry (DXA) has limited accessibility, so predictive models for hip osteoporosis that do not use bone mineral density (BMD) data are essential. We aimed to develop and validate prediction models for female hip osteoporosis using electronic health records without BMD data.

METHODS

This retrospective study used anonymized medical electronic records, from September 2013 to November 2023, from the Health Management Center of the Second Xiangya Hospital. A total of 8039 women were included in the derivation dataset. The set was then randomized into a 75% training dataset and a 25% testing dataset. Four algorithms for feature selection were used to identify predictors of osteoporosis. The identified predictors were then used to train and optimize eight machine learning models. The models were tuned using 5-fold cross-validation to assess model performance in the testing dataset and the independent validation dataset from the National Health and Nutrition Examination Surveys (NHANES). The SHapley Additive explanation (SHAP) method was used to rank feature importance and explain the final model.

RESULTS

A combination of the Boruta, LASSO, varSelRF, and RFE methods identified systolic blood pressure, red blood cell count, glycohemoglobin, alanine aminotransferase, aspartate aminotransferase, uric acid, age, and body mass index as the most important predictors of osteoporosis in women. The XGBoost model outperformed the other models, with an Area Under the Curve (AUC) of 0.805 (95%CI: 0.779-0.831), and a moderate sensitivity of 0.706. The externally validated XGBoost model had an AUC of 0.811 (95% CI: 0.793-0.828), with a moderate sensitivity of 0.775.

CONCLUSIONS

The XGBoost model demonstrates high identification performance even without questionnaire data, out-performing both the traditional the logistic regression model and the OSTA model. It can be integrated into routine clinical workflows to identify females at high risk for osteoporosis.

Optimal body mass index for protecting middle-aged and elderly patients with fatty liver from future fractures

OBJECTIVE

Previous studies have suggested that body mass index (BMI) should be considered when assessing the relationship between fatty liver (FL) and osteoporosis. The aim of this study was to investigate future fracture events in people with FL, focusing on the effect of BMI in both sexes.

METHODS

This retrospective cohort study from 2011 to 2019 enrolled 941 people, including 441 women and 500 men, aged 50 years or older who underwent liver imaging (ultrasound, computed tomography, or magnetic resonance image) and dual-energy X-ray absorptiometry (DXA, for bone mineral density measurements). The study examined predictors of osteoporosis in both sexes, and the effect of different ranges of BMI (18.5-24, 24-27, and ≥27 kg/m2 in women; 18.5-24, 24-27, 27-30 and ≥30 kg/m2 in men) on the risk of future fractures in FL patients.

RESULTS

The average follow-up period was 5.3 years for women and 4.2 years for men. Multivariate analysis identified age and BMI as independent risk factors for osteoporosis in both sexes. Each unit increase in BMI decreased the risk of osteoporosis by ≥10%. In both women and men with FL, a BMI of 24-27 kg/m2 offered protection against future fractures, compared to those without FL and with a BMI of 18.5-24 kg/m2.

CONCLUSION

The protective effect of a higher BMI against future fractures in middle-aged and elderly women and men with FL is not uniform and decreases beyond certain BMI ranges.

Relationships among body weight, lipids and bone mass in elderly individuals with fractures: A case-control study

BACKGROUND

The prevalence of osteoporosis and low bone mass is steadily rising each year. Low body weight is commonly linked to diminished bone mass and serves as a robust predictor of osteoporosis. Nonetheless, the connection between body mass index (BMI), bone mineral density, and lipid profiles among the elderly remains elusive.

AIM

To examine the association between BMI and bone mass, explore the correlation between lipid profiles and bone mass, and delve into the interplay between lipid metabolism and bone health.

METHODS

The study included 520 patients aged ≥ 65 years (178 men and 342 women). Age, sex, weight, and height were recorded. Femoral neck bone mineral density and T scores were determined using a dual-energy X-ray absorptiometry scanner. Blood calcium (Ca), phosphorus (P), albumin (ALB), alkaline phosphatase (ALP), aspartate aminotransferase, alanine aminotransferase, triglyceride (TG), total cholesterol (TC), high-density lipoprotein (HDL) and low-density lipoprotein (LDL) levels were measured. Patients were classified by sex (male and female), age (65-79 years and ≥ 80 years), and T score (normal bone mineral density, osteopenia and osteoporosis).

RESULTS

Age, sex, BMI, and ALP and TG levels were independent risk factors for osteoporosis. For the 65-79- and ≥ 80-year-old groups, females presented lower T scores than males. Ca, P, ALB, ALP, TC, HDL and LDL levels were significantly different between men and women in the 65-79-year-old group. In addition, BMI and TG levels were significantly decreased in osteoporotic patients compared with patients with normal bone mass. TC levels declined in 65- to 79-year-old male and female osteoporosis patients. In the group of women aged ≥ 80 years, osteoporotic patients showed significantly increased ALP levels. Furthermore, we found positive correlations between BMI and TG levels in the male and female patient groups. However, we found no significant differences in ALB, Ca, P, HDL and LDL levels in osteoporotic patients compared to patients with normal bone mass.

CONCLUSION

Osteoporotic patients showed significantly decreased BMI and TG levels compared with those with normal bone mass. BMI showed positive correlations with TG levels in male and female patients. These results indicate correlations between BMI and bone mass and between lipid profiles and bone mass.

Factors Associated With Trabecular Bone Score and Bone Mineral Density; A Machine Learning Approach

INTRODUCTION

Bone indexes including trabecular bone score (TBS) and bone mineral density (BMD) have been shown to be associated with wide spectrum of variables including physical activity, vitamin D, liver enzymes, biochemical measurements, mental and sleep disorders, and quality of life. Here we aimed to determine the most important factors related to TBS and BMD in SUVINA dataset.

METHODS

Data were extracted from the Survey of Ultraviolet Intake by Nutritional Approach (SUVINA study) including all 306 subjects entered this survey. All the available parameters in the SUVINA database were included the analysis. XGBoost modeler software was used to define the most important features associated with bone indexes including TBS and BMD in various sites.

RESULTS

Applying XGBoost modeling for 4 bone indexes indicated that this algorithm could identify the most important variables in relation to bone indexes with an accuracy of 92%, 93%, 90% and 90% respectively for TBS T-score, lumbar Z-score, neck of femur Z-score and Radius Z-score. Serum vitamin D, pro-oxidant-oxidant balance (PAB) and physical activity level (PAL) were the most important factors related to bone indices in different sites of the body.

CONCLUSIONS

Our findings indicated that XGBoost could identify the most important variables with an accuracy of >90% for TBS and BMD. The most important features associated with bone indexes were serum vitamin D, PAB and PAL.

Elevated gamma-glutamyl transpeptidase level is associated with an increased risk of hip fracture in postmenopausal women

The aim of this study was to evaluate the association between gamma-glutamyl transferase (GGT) levels and the risk of hip fracture among middle-aged women by using the Korean National Health Insurance Service claims database from 2002 to 2015. After exclusion of those with any chronic liver disease, heavy alcohol consumption, any missing values required for our analysis, or GGT levels less than 1 or greater than 99 percentile, we classified subjects into three groups according to baseline GGT levels. A total of 127,141 women aged 50 years or older were included for analysis (GGT range: 8–106 U/L). During an average 12.1 years of follow-up, 2758 patients sustained hip fractures (2.17%). Compared with the group in the lowest tertile, the group in the highest tertile had the highest cumulative incidence of hip fracture. One log-unit increase in GGT was associated with a 17% increased risk of hip fracture. Subgroup analysis by BMI (≥ 25 vs. < 25 kg/m²), presence of diabetes, levels of other liver enzymes, and alcohol consumption level did not show significant effect modification. In summary, elevated baseline GGT level was associated with an increased risk of hip fracture in postmenopausal women, independent of alcohol consumption and chronic liver disease.

Gamma-glutamyl-transferase is associated with incident hip fractures in women and men ≥ 50 years: a large population-based cohort study

The association of serum gamma-glutamyl-transferase (GGT) with hip fracture risk has not been examined in women and men ≥ 50 years. We show that elevated GGT was associated with increased hip fracture risk, particularly in men. GGT could be a candidate serum marker of long-term hip fracture risk in the elderly.

INTRODUCTION

We herein examined a possible relation between serum levels of GGT and hip fracture risk in women and men aged ≥ 50 years, which has not been investigated before.

METHODS

In this population-based prospective cohort study, approximately 41,000 women and nearly 33,000 men ≥ 50 years participating in a medical prevention program 1985-2005 in western Austria were followed up for the occurrence of osteoporotic hip fractures during 2003-2013. ICD-10 based discharge diagnoses for hip fracture included S72.0, S72.1, and S72.2 available from all regional hospitals. GGT-related hip fracture risk was ascertained at each participant´s first and last examination during the prevention program. In a subset of 5445 participants, alcohol consumption could be included as a covariate.

RESULTS

In men, hip fracture risk rose significantly by 75% and 86% for every tenfold increase of GGT measured at the first and last examination, respectively, and in women, hip fracture risk rose by 22% from the last examination. Elevated GGT (≥ 36 U/l in women, ≥ 56 U/l in men) at the first examination was associated with increased hip fracture risk only in men (HR 1.51, 95% CI 1.25-1.82), and at the last examination in both women (HR 1.14, 95% CI 1.02-1.28) and men (HR 1.61, 95% CI 1.33-1.95). Alcohol consumption had no significant influence on GGT-mediated hip fracture risk in women and men.

CONCLUSIONS

Our findings identified an association of elevated GGT and hip fracture in women and men ≥ 50 years and suggest GGT as a candidate serum marker of long-term hip fracture risk in an elderly population.

Inverse Relationship between Mean Corpuscular Volume and T-Score in Chronic Dialysis Patients

Background and Objectives: Osteoporosis and anemia are prevalent among chronic kidney disease stage 5D (CKD stage 5D) patients. Osteoblasts are known as the niche cells of hematopoietic stem cells (HSCs) and stimulate HSCs to form blood-cell lineages within bone marrow microenvironments. We hypothesized that an inverse correlation may exist between mean corpuscular volume (MCV), a surrogate for ineffective hematopoiesis, and bone mineral density (BMD) in the CKD stage 5D population. Materials and Methods: This is a cross-sectional designed cohort study evaluating CKD stage 5D patients who have received dialysis therapy for over three months. Baseline clinical characteristics and laboratory data were prospectively collected. The dual-energy X-ray absorptiometry (DXA) method was used to measure BMD at five sites, which were bilateral femoral neck, total hip, and lumbar spine 1–4. The Pearson correlation test was initially adopted, and a multivariate linear regression model was further applied for potential confounder adjustments. Results: From September 2020 to January 2021, a total of 123 CKD stage 5D patients were enrolled. The Pearson correlation test revealed a significant inverse association between MCV and BMD at bilateral femoral neck and lumbar spine. The lowest T-score of the five body sites was determined as the recorded T-score. After adjustments for several potential confounding factors, the multivariate linear regression model found consistent negative associations between T-score and MCV. Conclusions: The present study found significant inverse correlations between MCV and BMD at specific body locations in patients on dialysis. A decreased T-score was also found to be associated with macrocytosis after adjustments for confounding variables. However, direct evidence for the causative etiology was lacking.

Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis

The fracture risk of patients with diabetes is higher than those of patients without diabetes due to hyperglycemia, usage of diabetes drugs, changes in insulin levels, and excretion, and this risk begins as early as adolescence. Many factors including demographic data (such as age, height, weight, and gender), medical history (such as smoking, drinking, and menopause), and examination (such as bone mineral density, blood routine, and urine routine) may be related to bone metabolism in patients with diabetes. However, most of the existing methods are qualitative assessments and do not consider the interactions of the physiological factors of humans. In addition, the fracture risk of patients with diabetes and osteoporosis has not been further studied previously. In this paper, a hybrid model combining XGBoost with deep neural network is used to predict the fracture risk of patients with diabetes and osteoporosis, and investigate the effect of patients' physiological factors on fracture risk. A total of 147 raw input features are considered in our model. The presented model is compared with several benchmarks based on various metrics to prove its effectiveness. Moreover, the top 18 influencing factors of fracture risks of patients with diabetes are determined.

Association of bone mineral density with peripheral blood cell counts and hemoglobin in Chinese postmenopausal women: A retrospective study

Osteoporosis (OP) is a metabolic bone disease that can cause structural changes in bone marrow cavity. Bone marrow is the hematopoietic organ of adults. Accumulating evidence has shown a close connection between bone marrow hematopoietic function and bone formation. Some studies have revealed that OP is associated with hematopoiesis. However, the relationship is not definite.This study aimed to evaluate the association between peripheral blood cell counts (white blood cells [WBC], red blood cells [RBC], platelets [PLT]), hemoglobin [HGB], and bone mineral density [BMD]) in a sample of Chinese postmenopausal women. This is a retrospective study involving 673 postmenopausal women cases. The BMD of lumbar spine and left hip joint were measured by dual-energy X-ray absorptiometry. The levels of blood cell counts and HGB were measured and analyzed.The study results showed the WBC, RBC, PLT, and HGB levels of postmenopausal women in the OP group were all higher than those in the non-osteoporosis group. Spearman linear trend analysis and partial correlation analysis demonstrated that BMD was negatively correlated with WBC, RBC, PLT, and HGB in postmenopausal women.Due to the differences between different countries and races, and there are few studies on the association of BMD with peripheral blood cell counts and HGB in Chinese Postmenopausal Women. Therefore, more large sample studies are needed.