Diabetes mellitus, vitamin D & osteoporosis: Insights

Application of machine learning algorithms to predict osteoporosis in postmenopausal women with type 2 diabetes mellitus

PURPOSE

The screening and diagnosis of osteoporosis in patients with type 2 diabetes mellitus (T2DM) based on bone mineral density remains challenging because of the limited availability and accessibility of dual-energy X-ray absorptiometry. We aimed to develop and validate models to predict the risk of osteoporosis in postmenopausal women with T2DM based on machine learning (ML) algorithms.

METHODS

This retrospective study included 303 postmenopausal women with T2DM. To develop prediction models for osteoporosis, we applied nine ML algorithms combined with demographic, clinical, and laboratory data. The least absolute shrinkage and selection operator were used to perform feature selection. We used the bootstrap resampling technique for model training and validation. To test the performance of the models, we calculated indices including the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, calibration curve, and decision curve analysis. Furthermore, we conducted fivefold cross-validation for parameter optimization and model validation. Feature importance was assessed using the SHapley additive explanation (SHAP).

RESULTS

We identified 10 independent predictors as the most valuable features. An AUROC of 0.616-1.000 was observed for nine ML algorithms. The extreme gradient boosting (XGBoost) model exhibited the best performance, outperforming conventional risk assessment tools and registering 0.993 in the training set, 0.798 in the validation set, and 0.786 in the test set for fivefold cross-validation. Using SHAP, we found that the explanatory variables contributed to the model and their relationship with osteoporosis occurrence. Furthermore, we developed a user-friendly tool for calculating the risk of osteoporosis.

CONCLUSIONS

With the integration of demographic and clinical risk factors, ML algorithms can accurately predict osteoporosis. The XGBoost model showed ideal performance. With the incorporation of these models in the clinic, patients may benefit from early osteoporosis diagnosis and treatment.

Development of Machine Learning Models for Predicting Osteoporosis in Patients with Type 2 Diabetes Mellitus-A Preliminary Study

Purpose

Diagnosing osteoporosis in T2DM based on bone mineral density (BMD) remains challenging. We sought to develop prediction models employing machine learning algorithms for use as screening instruments for osteoporosis in T2DM patients.

Patients and Methods

Data were collected from 433 participants and analyzed using nine categorical machine learning algorithms to select features based on demographic and clinical variables. Multiple classification models were compared using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, sensitivity, specificity, the average precision (AP), precision, F1 score, precision-recall curves, calibration plots, and decision curve analysis (DCA) to determine the best model. In addition, 5-fold cross-validation was utilized to optimize the model, followed by an evaluation of feature significance using Shapley Additive exPlanations (SHAP). Using latent class analysis (LCA), distinct subpopulations were identified by constructing several discrete clusters.

Results

In this study, nine feature variables were identified to construct predictive models for osteoporosis in individuals with T2DM. The machine learning algorithms achieved an AP range of 0.444-1.000. The XGBoost model was selected as the final prediction model with an AUROC of 0.940 in the training set, 0.772 in the validation set for 5-fold cross-validation, and 0.872 in the test set. Using SHAP methodology, 25(OH)D was identified as the most important risk factor. Additionally, a 3-Class model was constructed using LCA, which categorized individuals into high, medium, and low-risk groups.

Conclusion

Our study developed a predictive model with high accuracy and clinical validity for predicting osteoporosis in type 2 diabetes patients. We also identified three subpopulations with varying osteoporosis risk using clustering. However, limited sample size warrants cautious interpretation of results, and validation in larger cohorts is needed.

The protective effect of green tea on diabetes-induced hepato-renal pathological changes: a histological and biochemical study

We investigated the protective effect of green tea on diabetic hepato-renal complications. Thirty male Wistar rats were randomly divided into five equal groups: normal control, diabetic control, glibenclamide-treated, green tea-treated, and combined therapy-treated groups; ethical approval number "BERC-014-01-20." After eight weeks, animals were sacrificed by CO₂ euthanasia method, liver and kidney tissues were processed and stained for pathological changes, and blood samples were collected for biochemical analysis. Diabetic rats showed multiple hepato-renal morphological and apoptotic changes associated with significantly increased some biochemical parameters, while serum albumin and HDL decreased significantly compared to normal control (p < .05). Monotherapy can induce significant improvements in pathological and biochemical changes but has not been able to achieve normal patterns. In conclusion, green tea alone has a poor hypoglycaemic effect but can reduce diabetic complications, whereas glibenclamide cannot prevent diabetic complications. The addition of green tea to oral hypoglycaemic therapy has shown a potent synergistic effect.

Absence of Vitamin D Deficiency Among Outdoor Workers With Type 2 Diabetes Mellitus in Southern West Bengal, India

Background: Vitamin D deficiency is widespread globally and is associated with type 2 diabetes mellitus (T2DM). Studies suggest markedly lower prevalence of vitamin D deficiency in outdoor workers compared to indoor workers. However, data on the vitamin D status of outdoor workers with T2DM is lacking.

Aims: We assessed the vitamin D status of outdoor workers with T2DM residing across several districts of Southern West Bengal, India.

Design: The present study is a descriptive observational study.

Material and methods: A total of 128 outdoor workers with T2DM were assessed for serum 25-hydroxyvitamin D (25(OH)D) during December 2019 after excluding common confounders except sun exposure (which was detailed using a questionnaire). Hospital staff were indoor controls, and vitamin D status was classified as per the Institute of Medicine guidelines.

Results: The mean serum 25(OH)D of outdoor workers with T2DM was 21.79 ± 6.31 ng/mL, with only 2.34% (n = 3) having vitamin D deficiency and 57.03% (n = 73) having sufficient serum 25(OH)D levels. The mean serum 25(OH)D of indoor controls was significantly lower at 16.67 ± 9.82 ng/mL (p = 0.003), with 33.33% being vitamin D deficient. Serum 25(OH)D in outdoor workers with T2DM did not have a significant correlation with indices of sun exposure.

Conclusions: Vitamin D deficiency is practically absent in outdoor workers with T2DM residing in Southern West Bengal, India.

Vitamin D Supplementation Could Enhance the Effectiveness of Glibenclamide in Treating Diabetes and Preventing Diabetic Nephropathy: A Biochemical, Histological and Immunohistochemical Study

Diabetes mellitus is an oxidative stress-related disease characterized by hyperglycemia and a variety of complications, including nephropathy. Vitamin D has variable functions extending beyond the calcium metabolism to prevent oxidative tissue damage. We aimed to investigate whether vitamin D supplements could enhance Glibenclamide's effectiveness in treating diabetes and minimize the risk of associated pathology. Wistar rats were divided into normal control (n = 10) and diabetic (n = 30), where animals received two low doses of Streptozotocin 30 mg/kg/BW intraperitoneally to develop diabetes. The diabetic rats were then randomly divided into three equal groups: untreated, treated with Glibenclamide (0.6 mg/kg), and treated with Glibenclamide and Vitamin D3 (500 IU/kg). After eight weeks, the animals were sacrificed, and blood samples and kidney tissues were collected to evaluate biochemical, anti-oxidant, and pro-inflammatory cytokine levels and histological and immunohistochemical changes. Diabetic animals had significantly increased fasting blood glucose, lipid profile, blood urea, serum creatinine, and Malondialdehyde levels, whereas serum insulin, albumin, and the anti-oxidant enzymes superoxide dismutase and catalase were significantly decreased compared to normal control (p < 0.01). Furthermore, some renal histological changes were observed together with significantly increased immunoreactivity of anti-p53, anti-TNF-α, and anti-IL-6 antibodies when compared to the normal control. All abnormal parameters improved significantly with Glibenclamide therapy (p < 0.01), but combination therapy with vitamin D produced a much better result. In conclusion, vitamin D supplementation along with anti-diabetic medication can help prevent or reduce the severity of diabetic nephropathy due to its potent antioxidant, anti-inflammatory, and anti-apoptotic properties.

Glycolipid toxicity induces osteogenic dysfunction via the TLR4/S100B pathway

Diabetes can cause bone metabolism disorders and osteoporosis. The occurrence of both diabetes mellitus and osteoporosis increases the disability and mortality of elderly individuals due to pathological fracture. Abnormal metabolism of nutrientsis considered to be one of the important mechanisms of diabetes mellitus-induced osteoporosis. This study preliminarily explored the roles of TLR4 (Toll-like receptor 4) and S100B in osteogenic dysfunction induced by glycolipid toxicity. In this study, a diabetic rat model and TLR4-knockdown diabetic rat model were used in vivo. MC3T3-E1 cells in a high glucose and palmitic acid environment were used as glycolipid toxicity cell models in vitro. We investigated the effects of TLR4 and S100B on osteogenesis by overexpression or inhibition of TLR4 and S100B in vitro. We found that when TLR4 or S100B was inhibited, ALP and OCN were significantly up-regulated and p-ERK was significantly down regulated in the glycolipid model. These results suggest that TLR4/S100B may play a role in reducing glycolipid toxicity by regulating ERK phosphorylation.

Is diabetes mellitus a risk factor for low bone density: a systematic review and meta-analysis

BACKGROUND

This systematic review aimed to investigate whether diabetes mellitus is a risk factor for low bone density, as this might be important and necessary for doctors specialized in treating patients with low bone density.

METHODS

PubMed, Embase, CINAHL, and SciELO were searched for cohort, case-control, and cross-sectional studies that investigated the effects of diabetes mellitus on bone mineral density till January 2020. Data screening and extraction are done independently, whereas the methodological quality of the studies was assessed according to the Newcastle-Ottawa Scale (NOS).

RESULTS

A total of 14 studies that met the eligibility criteria including 24,340 participants were enrolled. The overall quality of the studies had a scale of over 6 points. The overall odds ratio (OR) regarding the risk of diabetes mellitus in low bone density patients was 1.20 [95% confidence interval (CI)0.80-1.79, P = 0.30], and type 2 diabetes mellitus (T2DM) (OR = 0.69 [0.11, 4.55], P = 0.70). Subgroup analysis revealed that whether females or males, developed or developing countries, T2DM, studies after 2015, and quality over 7 points (all P values > 0.05) showed no significant differences with the risk of low bone density, except type 1 diabetes mellitus (T1DM) (OR = 3.83 [1.64, 8.96], P = 0.002), and studies before 2015 (OR = 1.76 [1.06, 2.92], P = 0.03), and quality below 7 points (OR = 2.27 [1.50, 3.43], P = 0.0001). Funnel plot showed no significant asymmetry.

CONCLUSIONS

These findings revealed no relationship between T2DM and low bone density, and also, the evidence between T1DM and low bone density is inadequate, requiring further analysis of well-designed cohort studies.

Differential responses of bone to angiotensin II and angiotensin(1-7): beneficial effects of ANG(1-7) on bone with exposure to high glucose

Osteoporosis, diabetes, and hypertension are common concurrent chronic disorders. This study aimed to explore the respective effects of angiotensin II (ANG II) and angiotensin(1-7) [ANG(1-7)], active peptides in the renin-angiotensin system, on osteoblasts and osteoclasts under high-glucose level, as well as to investigate the osteo-preservative effects of ANG II type 1 receptor (AT1R) blocker and ANG(1-7) in diabetic spontaneously hypertensive rats (SHR). ANG II and ANG(1-7), respectively, decreased and increased the formation of calcified nodules and alkaline phosphatase activity in MC3T3-E1 cells under high-glucose level, and respectively stimulated and inhibited the number of matured osteoclasts and pit resorptive area in RANKL-induced bone marrow macrophages. Olmesartan and Mas receptor antagonist A779 could abolish those effects. ANG II and ANG(1-7), respectively, downregulated and upregulated the expressions of osteogenesis factors in MC3T3-E1 cells. ANG II promoted the expressions of cathepsin K and MMP9 in RAW 264.7 cells, whereas ANG(1-7) repressed these osteoclastogenesis factors. ANG II rapidly increased the phosphorylation of Akt and p38 in RAW 264.7 cells, whereas ANG(1-7) markedly reduced the phosphorylation of p38 and ERK under high-glucose condition. After treatments of diabetic SHR with valsartan and ANG(1-7), a significant increase in trabecular bone area, bone mineral density, and mechanical strength was only found in the ANG(1-7)-treated group. Treatment with ANG(1-7) significantly suppressed the increase in renin expression and ANG II content in the bone of SHR. Taken together, ANG II/AT1R and ANG(1-7)/Mas distinctly regulated the differentiation and functions of osteoblasts and osteoclasts upon exposure to high-glucose condition. ANG(1-7) could protect SHR from diabetes-induced osteoporosis.