Risk Profiles for Weight Gain among Postmenopausal Women: A Classification and Regression Tree Analysis Approach

Jung, Su Yon; Vitolins, Mara Z.; Fenton, Jenifer I.; Frazier‐Wood, Alexis C.; Hursting, Stephen D.; Chang, Shine

doi:10.1371/journal.pone.0121430

Cited by 25 publications

(21 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, more women than men experienced various eating disorders, which can be associated with a greater desire to maintain low body weight, especially in young women [34]. Among postmenopausal women, there was an increased risk of weight gain [35]. The increased risk of BMI ≥ 25 kg/m 2 with age has also been confirmed in the study sample.…”

Section: Discussionmentioning

confidence: 66%

Diet-Related Factors, Physical Activity, and Weight Status in Polish Adults

et al. 2019

View full text Add to dashboard Cite

Obesity is a serious problem for both the individual and society due to its health and economic consequences. Therefore, there is a need to focus on factors which explain this phenomenon and may be useful in preventing future occurrence. The aim of this study was to determine the lifestyle factors coexisting with increased body mass index (BMI ≥ 25 kg/m2) in Polish adults, including factors related to diet (dietary patterns—DPs; dietary restrictions; number of meals; frequency of snacking, eating out, and ordering home delivery meals), physical activity, and sociodemographic characteristics. A cross-sectional quantitative survey was carried out in 2016 amongst 972 Polish adults under the Life Style Study (LSS). To determine the factorscoexisting with BMI ≥ 25 kg/m2, the logistic regression model was developed. Women were less likely to be overweight or obese compared to men. The likelihood of BMI ≥ 25 kg/m2 increased with age by 4% in each subsequent year of life. Frequent consumption of fruits and vegetables, adhering to restrictions in quantity of food consumed and at least moderate physical activity during leisure time decreased the likelihood of BMI ≥ 25 kg/m2. More frequent consumption of meat and eating five or more meals a day increased the likelihood of BMI ≥ 25 kg/m2. Diet-related factors explained the developed model better than factors related to physical activity, however, age and gender were the factors most strongly correlated with BMI ≥ 25 kg/m2. Therefore, development of strategies to prevent and reduce overweight and obesity should focus on the demographic characteristics of the population, and then on teaching behaviors conducive for reducing the amount of food consumed, especially meat. However, physical activity in leisure time should also be included in the prevention of obesity.

show abstract

Section: Discussionmentioning

confidence: 66%

Diet-Related Factors, Physical Activity, and Weight Status in Polish Adults

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Our objective was to be able to identify subpopulations or ‘phenotypes’ within a large population of postmenopausal women from the Women’s Health Initiative-Observational Study (WHI OS), based on the relationship between body weight and dietary macronutrients, physical activity, and socioeconomic variables. Machine learning has been used in the past to determine dietary factors that are associated with a risk of weight gain in postmenopausal women from WHI OS [10], however, we took a different approach. We trained machine learning algorithms on the macronutrient composition of diets and physical activity, as well as other pertinent demographic data, to predict current body weight.…”

Section: Introductionmentioning

confidence: 99%

Phenotyping Women Based on Dietary Macronutrients, Physical Activity, and Body Weight Using Machine Learning Tools

2019

View full text Add to dashboard Cite

Nutritional phenotyping can help achieve personalized nutrition, and machine learning tools may offer novel means to achieve phenotyping. The primary aim of this study was to use energy balance components, namely input (dietary energy intake and macronutrient composition) and output (physical activity) to predict energy stores (body weight) as a way to evaluate their ability to identify potential phenotypes based on these parameters. From the Women’s Health Initiative Observational Study (WHI OS), carbohydrates, proteins, fats, fibers, sugars, and physical activity variables, namely energy expended from mild, moderate, and vigorous intensity activity, were used to predict current body weight (both as body weight in kilograms and as a body mass index (BMI) category). Several machine learning tools were used for this prediction. Finally, cluster analysis was used to identify putative phenotypes. For the numerical predictions, the support vector machine (SVM), neural network, and k-nearest neighbor (kNN) algorithms performed modestly, with mean approximate errors (MAEs) of 6.70 kg, 6.98 kg, and 6.90 kg, respectively. For categorical prediction, SVM performed the best (54.5% accuracy), followed closely by the bagged tree ensemble and kNN algorithms. K-means cluster analysis improved prediction using numerical data, identified 10 clusters suggestive of phenotypes, with a minimum MAE of ~1.1 kg. A classifier was used to phenotype subjects into the identified clusters, with MAEs <5 kg for 15% of the test set (n = ~2000). This study highlights the challenges, limitations, and successes in using machine learning tools on self-reported data to identify determinants of energy balance.

show abstract

“…Interestingly, the signi cance of trust was not found in the adjusted logistic regression model, however, it was observed in the CART model. We suggest that the role of trust may depend on the appearance of other social capital dimensions and variables, which emphasizes the effectiveness of the CART model in examining the complex interactions among multiple variables that may be overlooked in the conventional analytical approach [26]. The importance of this nding lies in adding a scienti c explanation of using the CART model to help examine the association between social capital and loneliness while revealing how social capital interacts with other factors and produces an effect on the development of loneliness.…”

Section: Discussionmentioning

confidence: 95%

“…Collectively, a more accurate and comprehensive analytical approach exploring the interaction of different variables that prompt health outcomes in the older population is proposed. [26]. Exploring multiple interactions is fundamental in obtaining the most targeted and effectual interventions to reduce the onset of loneliness and these ndings may be valuable in developing appropriate intervention measures or programs to prevent the incidence of loneliness.…”

Section: Introductionmentioning

confidence: 99%

Association between social capital and loneliness among older adults: A cross-sectional study in Anhui Province, China

Bai

Wang

Shao

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: We aimed to examine the association between social capital and loneliness in Anhui Province, China. Methods: Data were collected from a cross-sectional study using a multi-stage stratified cluster sampling strategy. Data on demographic characteristics, socioeconomic factors, social capital, and loneliness in 1810 older adults (aged 60 years and older) were used for analysis. Binary logistic regression models and a classification and regression tree model were performed to assess the association of social capital and loneliness. Results: Our results indicated that social capital in terms of lower level of social participation (AOR = 1.38; 95% CI: 1.10-1.74), social connection (AOR = 1.51; 95% CI: 1.18-1.93), and reciprocity (AOR = 1.47; 95% CI: 1.13-1.90) were associated with higher odds of developing loneliness. We noted the interactive effect of different social capital dimensions on loneliness, suggesting that the risk for suffering loneliness was greatest in older people limited in functional ability, with less trust, less social connection, and less social participation. Conclusions: Our findings show that social capital is associated with loneliness in older adults. This implies that social capital, especially in terms of trust, social connection, and social participation may be significant for alleviating loneliness in later life.

show abstract

Risk Profiles for Weight Gain among Postmenopausal Women: A Classification and Regression Tree Analysis Approach

Cited by 25 publications

References 40 publications

Diet-Related Factors, Physical Activity, and Weight Status in Polish Adults

Diet-Related Factors, Physical Activity, and Weight Status in Polish Adults

Phenotyping Women Based on Dietary Macronutrients, Physical Activity, and Body Weight Using Machine Learning Tools

Association between social capital and loneliness among older adults: A cross-sectional study in Anhui Province, China

Contact Info

Product

Resources

About