scholarly journals Machine Learning Reveals Influence of Stool pH on Bone Mineral Density in a Healthy Multi-Ethnic U.S. Population

2021 ◽  
Vol 5 (Supplement_2) ◽  
pp. 8-8
Author(s):  
Elizabeth Chin ◽  
Marta Van Loan ◽  
Sarah Spearman ◽  
Ellen Bonnel ◽  
Kevin Laugero ◽  
...  
Keyword(s):  
Machine Learning ◽  
Bone Mineral Density ◽  
Bone Mineral ◽  
Bone Health ◽  
Whole Body ◽  
Fiber Intake ◽  
Learning Models ◽  
Mineral Density ◽  
Modifiable Factors ◽  
Machine Learning Models

Abstract Objectives A variety of modifiable and non-modifiable factors such as ethnicity, age, and diet have been shown to influence bone health. Previous studies are usually limited to analyses focused on the association of a few a priori variables or on a specific subset of the population. The objective of this study was to use dietary, physiological, and lifestyle data to identify directly modifiable and non-modifiable variables predictive of bone mineral content (BMC) and bone mineral density (BMD) in healthy US men and women using machine learning models. Methods Ridge, lasso, elastic net, and random forest models were used to predict whole-body, femoral neck, and spine BMC and BMD in healthy US adults (n = 313) using non-modifiable anthropometric, physiological, and demographic variables, directly modifiable lifestyle (physical activity, tobacco use) and dietary (nutrient or food groups intake via food frequency questionnaire) variables, and variables approximating directly modifiable behavior (circulating vitamin D and stool pH). Model feature importances were used to identify variables useful for predicting BMC and BMD. Results Machine learning models using non-modifiable variables explained more variation in BMC and BMD (highest R2 = 0.750) compared to when using only directly modifiable variables (highest R2 = 0.107). Machine learning models had better performance compared to multivariate linear regression, which had lower predictive value (highest R2 = 0.063) when using directly modifiable variables only. BMI, body fat %, height, and menstruation history were predictors of BMC and BMD. For the directly modifiable features, betaine, cholesterol, hydroxyproline, menaquinone-4, dihydrophylloquinone, eggs, cheese, cured meat, refined grains, fruit juice, and alcohol consumption were predictors of BMC and BMD. Low stool pH, a proxy for fermentable fiber intake, was also predictive of higher BMC and BMD. Conclusions Machine learning models can be used to identify previously unforeseen variables that may contribute to bone health. Modifiable factors explained less variation in the data compared to other features. Low stool pH, which has been shown to be associated with fermentable fiber intake, short chain fatty acid production, and enhanced calcium absorption, was associated with higher BMC and BMD in a healthy US population. Funding Sources USDA-ARS

scholarly journals Inulin supplementation reduces the negative effect of a high-fat diet rich in SFA on bone health of growing pigs

2018 ◽  
Vol 119 (10) ◽  
pp. 1111-1118 ◽  
Author(s):  
Monika Sobol ◽  
Stanisława Raj ◽  
Grzegorz Skiba
Keyword(s):  
Bone Mineral Density ◽  
Bone Mineral ◽  
Bone Health ◽  
High Fat Diet ◽  
Growing Pigs ◽  
Whole Body ◽  
Standard Diet ◽  
High Fat ◽  
Mineral Density ◽  
Negative Effect

AbstractConsumption of a high-fat diet, rich in SFA, causes deterioration of bone properties. Some studies suggest that feeding inulin to animals may increase mineral absorption and positively affect bone quality; however, these studies have been carried out only on rodents fed a standard diet. The primary objective of this study was to determine the effect of inulin on bone health of pigs (using it as an animal model for humans) fed a high-fat diet rich in SFA, having an unbalanced ratio of lysine:metabolisable energy. It was hypothesised that inulin reduces the negative effects of such a diet on bone health. At 50 d of age, twenty-one pigs were randomly allotted to three groups: the control (C) group fed a standard diet, and two experimental (T and TI) groups fed a high-fat diet rich in SFA. Moreover, TI pigs consumed an extra inulin supply (7 % of daily feed intake). After 10 weeks, whole-body bone mineral content (P=0·0054) and bone mineral density (P=0·0322) were higher in pigs of groups TI and C compared with those of group T. Femur bone mineral density was highest in pigs in group C, lower in group TI and lowest in group T (P=0·001). Femurs of pigs in groups TI and C had similar, but higher, maximum strength compared with femurs of pigs in group T (P=0·0082). In conclusion, consumption of a high-fat diet rich in SFA adversely affected bone health, but inulin supplementation in such a diet diminishes this negative effect.

Genetically determined SCFA concentration modifies the association of dietary fiber intake with changes in bone mineral density during weight loss: The Preventing Overweight Using Novel Dietary Strategies (POUNDS LOST) trial

2021 ◽  
Author(s):  
Tao Zhou ◽  
Dianjianyi Sun ◽  
Xiang Li ◽  
Yoriko Heianza ◽  
Meryl S LeBoff ◽  
...  
Keyword(s):  
Bone Mineral Density ◽  
Weight Loss ◽  
Dietary Fiber ◽  
Bone Mineral ◽  
Genetic Variants ◽  
Whole Body ◽  
Fiber Intake ◽  
Mineral Density ◽  
Dietary Fiber Intake ◽  
Dietary Strategies

ABSTRACT Background SCFAs are involved in regulation of body weight and bone health. Objectives We aimed to examine whether genetic variations related to butyrate modified the relation between dietary fiber intake and changes in bone mineral density (BMD) in response to weight-loss dietary interventions. Methods In the 2-y Preventing Overweight Using Novel Dietary Strategies trial, 424 participants with BMD measured by DXA scan were randomly assigned to 1 of 4 diets varying in macronutrient intakes. A polygenic score (PGS) was calculated based on 7 genetic variants related to the production of butyrate for 370 of the 424 participants. Results SCFA PGS significantly modified the association between baseline dietary fiber intake and sex on 2-y changes in whole-body BMD (P-interaction = 0.049 and 0.008). In participants with the highest tertile of SCFA PGS, higher dietary fiber intake was related to a greater increase in BMD (β:  0.0022; 95% CI: 0.0009, 0.0035; P = 0.002), whereas no such association was found for participants in the lower tertiles. In the lowest tertiles of SCFA PGS, men showed a significant increase in whole-body BMD (β: 0.0280; 95% CI: 0.0112, 0.0447; P = 0.002) compared with women. In the highest tertile, no significant difference was found for the change in BMD between men and women. Conclusions Our data indicate that genetic variants related to butyrate modify the relations of dietary fiber intake and sex with long-term changes in BMD in response to weight-loss diet interventions.

scholarly journals Exploring the Relationships Among the Inflammatory Potential of the Diet, Bone Mineral Density, and Injury Incidence in Collegiate Athletes (P23-006-19)

2019 ◽  
Vol 3 (Supplement_1) ◽  
Author(s):  
Kiley Field ◽  
John Gieng ◽  
Giselle Pignotti ◽  
Sofia Apsey
Keyword(s):  
Bone Mineral Density ◽  
Bone Mineral ◽  
Bone Health ◽  
Collegiate Athletes ◽  
Whole Body ◽  
Research Centre ◽  
Injury Incidence ◽  
Mineral Density ◽  
The Relationship ◽  
Prior Injury

Abstract Objectives The relationship between the inflammatory potential of the diet, estimated by the Dietary Inflammatory Index (DII) score, and bone health has been studied in older populations and suggests that the diet can influence bone mineral density (BMD) and fracture risk. These relationships have yet to be explored in other potentially vulnerable populations, such as athletes, where risk of injuries may be more common due to high physical stresses and over-use. The aims of this study were 1) to examine the correlation between DII scores, and BMD in collegiate athletes, and 2) to assess the relationship between DII score and self-reported prior injury incidence. Methods Healthy collegiate athletes (n = 43) were recruited for this study: football, n = 12; men's soccer, n = 2; women's soccer, n = 13; women's swimming, n = 12; and women's basketball, n = 4. For each athlete, three 24-hour dietary intakes were collected using a standardized multiple-pass interview methodology (Nutrition Data System for Research) and this data was used to calculate individual DII scores. Body composition, including whole-body sub-total BMD, was measured using dual-energy X-ray absorptiometry. A modified overuse injury questionnaire (Oslo Sports Trauma Research Centre) was used to assess incidence of injuries in the prior 12 months. Results The participants (n = 14 male, n = 29 female) had a mean age of 19.4 ± 1.1 yrs and BMI of 25.8 ± 4.1 kg/m2. Mean DII score was −0.43 ± 0.17 points (range: −3.94 to 4.34). Mean BMD was 1.251 ± 0.169 g/cm2. Overall, DII score and BMD was not correlated (P = 0.47). Furthermore, DII scores of athletes that reported no prior injury did not differ from those who reported 1 or more injuries. Conclusions Unlike research in postmenopausal women, it appears that bone health of young healthy athletes is less vulnerable to the influence of diets with higher inflammatory potential. Moreover, the lack of difference in DII score among athletes reporting various levels of prior injury suggests that the inflammatory potential of the diet is a poor predictor of injury risk in collegiate athletes. Funding Sources N/A.

scholarly journals Comparison of Machine Learning Approaches in Prediction of Bone Mineral Density in Elderly Men

2020 ◽  
Author(s):  
Qing Wu ◽  
Fatma Nasoz ◽  
Jongyun Jung ◽  
Bibek Bhattarai
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Bone Mineral Density ◽  
Random Forest ◽  
Linear Regression ◽  
Genomic Data ◽  
Gradient Boosting ◽  
Learning Models ◽  
Mineral Density ◽  
Machine Learning Models

AbstractBone mineral density (BMD) is a highly heritable trait with heritability ranging from 50% to 80%. Numerous BMD-associated Single Nucleotide Polymorphisms (SNPs) were discovered by GWAS and GWAS meta-analysis. However, several studies found that combining these highly significant SNPs together only explained a small percentage of BMD variance. This inconsistency may be caused by limitations of the linear regression approaches employed because these traditional approaches lack the flexibility and the adequacy to model complex gene interactions and regulations. Hence, we developed various machine learning models of genomic data and ran experiments to identify the best machine learning model for BMD prediction at three different sites. We used genomic data of Osteoporotic Fractures in Men (MrOS) cohort Study (N=5,133) for analysis. Genotype imputation was conducted at the Sanger Imputation Server. A total of 1,103 BMD-associated SNPs were identified and corresponding weighted genetic risk scores were calculated. Genetic variants, as well as age and other traditional BMD predictors, were included for modeling. Data were normalized and were split into a training set (80%) and a test set (20%). BMD prediction models were built separately by random forest, gradient boosting, and neural network algorithms. Linear regression was used as a reference model. We applied the non-parametric Wilcoxon signed-rank tests for the measurement of MSE in each model for the pair-wise model comparison. We found that gradient boosting shows the lowest MSE for each BMD site and a prediction model built using the machine learning models achieves improved performance when a large number of SNPs are included in the models. With the predictors of phenotype covariate + 1,103 SNPs, all of the models were statistically significant except neural network vs. random forest at femoral neck BMD and gradient boosting vs. random forest at total hip BMD.

scholarly journals Status of bone health and association of socio-demographic characteristics with Bone Mineral Density in Pakistani Females

2019 ◽  
Vol 35 (3) ◽  
Author(s):  
Saba Tariq ◽  
Mukhtiar Baig ◽  
Sundus Tariq ◽  
Muhammad Shahzad
Keyword(s):  
Bone Mineral Density ◽  
Primary Education ◽  
Bone Mineral ◽  
Bone Health ◽  
Mass Density ◽  
Univariate Analysis ◽  
Demographic Characteristics ◽  
Bone Mass Density ◽  
Mineral Density ◽  
Modifiable Factors

Background & Objective: The “silent thief” of bone osteoporosis is associated with various modifiable factors, identifying these factors is important in decreasing the prevalence of this highly prevalent disease. Therefore, this study was planned to identify these risk factors for osteoporosis in premenopausal and postmenopausal Pakistani women. Methods: A total of 1205 pre and postmenopausal females between the age of 20 to 80 years were selected. Detailed history about the socio-demographic characteristics including age, education, profession, marital and resident status was recorded. Medical and gynecological history was also taken after informed consent Bone health of females was assessed using calcaneal ultrasound bone densitometer. SPSS 22.0 was used to analyze data. Results: Univariate analysis showed that age (30-39 yrs, and 60-69 yrs), occupation (housewives) and education (secondary and primary education, illiterate) were significantly associated with low bone mass density (LBMD). Multivariate analysis showed that age 30-39 years (OR=0.25 95%CI 0.13 – 0.49), age 40-49 years (OR=0.30 95%CI 0.15 – 0.59), age 50-59 years (OR=0.42 95%CI 0.22 – 0.79), primary education (OR=3.83, 95%CI 2.30 - 6.38) and illiteracy (OR=3.83 95%CI 2.52 – 5.82), were significantly associated with LBMD. The prevalence of osteopenia and osteoporosis was 29.8%, 27.2%, respectively, while 43% of subjects had normal BMD. Conclusion: It is concluded that within Pakistani population, the prevalence of osteopenia is high even at an early age group and the odds of having LBMD are more in less educated or illiterate women. doi: https://doi.org/10.12669/pjms.35.3.551 How to cite this:Tariq S, Baig M, Tariq S, Shahzad M. Status of bone health and association of socio-demographic characteristics with Bone Mineral Density in Pakistani Females. Pak J Med Sci. 2019;35(3):---------. doi: https://doi.org/10.12669/pjms.35.3.551 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Effect of 12 months of creatine supplementation and whole-body resistance training on measures of bone, muscle and strength in older males

2020 ◽  
pp. 026010602097524
Author(s):  
Darren G Candow ◽  
Philip D Chilibeck ◽  
Julianne Gordon ◽  
Emelie Vogt ◽  
Tim Landeryou ◽  
...  
Keyword(s):  
Bone Mineral Density ◽  
Resistance Training ◽  
Bone Mineral ◽  
Creatine Supplementation ◽  
Whole Body ◽  
Mineral Density ◽  
Geometric Properties ◽  
Section Modulus ◽  
Body Resistance ◽  
Older Males

Background: The combination of creatine supplementation and resistance training (10–12 weeks) has been shown to increase bone mineral content and reduce a urinary indicator of bone resorption in older males compared with placebo. However, the longer-term effects (12 months) of creatine and resistance training on bone mineral density and bone geometric properties in older males is unknown. Aim: To assess the effects of 12 months of creatine supplementation and supervised, whole-body resistance training on bone mineral density, bone geometric properties, muscle accretion, and strength in older males. Methods: Participants were randomized to supplement with creatine ( n = 18, 49–69 years, 0.1 g·kg-1·d-1) or placebo ( n = 20, 49–67 years, 0.1 g·kg-1·d-1) during 12 months of supervised, whole-body resistance training. Results: After 12 months of training, both groups experienced similar changes in bone mineral density and geometry, bone speed of sound, lean tissue and fat mass, muscle thickness, and muscle strength. There was a trend ( p = 0.061) for creatine to increase the section modulus of the narrow part of the femoral neck, an indicator of bone bending strength, compared with placebo. Adverse events did not differ between creatine and placebo. Conclusions: Twelve months of creatine supplementation and supervised, whole-body resistance training had no greater effect on measures of bone, muscle, or strength in older males compared with placebo.

scholarly journals Somatic maturation and the relationship between bone mineral variables and types of sports among adolescents: cross-sectional study

2017 ◽  
Vol 135 (3) ◽  
pp. 253-259 ◽  
Author(s):  
Ricardo Ribeiro Agostinete ◽  
Igor Hideki Ito ◽  
Han Kemper ◽  
Carlos Marcelo Pastre ◽  
Mário Antônio Rodrigues-Júnior ◽  
...  
Keyword(s):  
Bone Mineral Density ◽  
Bone Mineral ◽  
Peak Height ◽  
Cross Sectional Study ◽  
Height Velocity ◽  
Whole Body ◽  
Sectional Study ◽  
Peak Height Velocity ◽  
Mineral Density ◽  
Cross Sectional

ABSTRACT CONTEXT AND OBJECTIVE: Peak height velocity (PHV) is an important maturational event during adolescence that affects skeleton size. The objective here was to compare bone variables in adolescents who practiced different types of sports, and to identify whether differences in bone variables attributed to sports practice were dependent on somatic maturation status. DESIGN AND SETTING: Cross-sectional study, São Paulo State University (UNESP). METHODS: The study was composed of 93 adolescents (12 to 16.5 years old), divided into three groups: no-sport group (n = 42), soccer/basketball group (n = 26) and swimming group (n = 25). Bone mineral density and content were measured using dual-energy x-ray absorptiometry and somatic maturation was estimated through using peak height velocity. Data on training load were provided by the coaches. RESULTS: Adolescents whose PHV occurred at an older age presented higher bone mineral density in their upper limbs (P = 0.018). After adjustments for confounders, such as somatic maturation, the swimmers presented lower values for bone mineral density in their lower limbs, spine and whole body. Only the bone mineral density in the upper limbs was similar between the groups. There was a negative relationship between whole-body bone mineral content and the weekly training hours (β: -1563.967; 95% confidence interval, CI: -2916.484 to -211.450). CONCLUSION: The differences in bone variables attributed to sport practice occurred independently of maturation, while high training load in situations of hypogravity seemed to be related to lower bone mass in swimmers.

Sign in / Sign up

Export Citation Format

Share Document