Dataset Information

Variable selection and importance in presence of high collinearity: an application to the prediction of lean body mass from multi-frequency bioelectrical impedance.

ABSTRACT: In prediction problems both response and covariates may have high correlation with a second group of influential regressors, that can be considered as background variables. An important challenge is to perform variable selection and importance assessment among the covariates in the presence of these variables. A clinical example is the prediction of the lean body mass (response) from bioimpedance (covariates), where anthropometric measures play the role of background variables. We introduce a reduced dataset in which the variables are defined as the residuals with respect to the background, and perform variable selection and importance assessment both in linear and random forest models. Using a clinical dataset of multi-frequency bioimpedance, we show the effectiveness of this method to select the most relevant predictors of the lean body mass beyond anthropometry.

SUBMITTER: Cammarota C

PROVIDER: S-EPMC9042145 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Variable selection and importance in presence of high collinearity: an application to the prediction of lean body mass from multi-frequency bioelectrical impedance.

Cammarota Camillo C Pinto Alessandro A

Journal of applied statistics 20200513 9

In prediction problems both response and covariates may have high correlation with a second group of influential regressors, that can be considered as background variables. An important challenge is to perform variable selection and importance assessment among the covariates in the presence of these variables. A clinical example is the prediction of the lean body mass (response) from bioimpedance (covariates), where anthropometric measures play the role of background variables. We introduce a re ...[more]

PMID: 35706573

Similar Datasets

Project description:IntroductionMethods of body composition estimation such as dual-energy X-ray absorptiometry (DXA), anthropometry, and bioimpedance (BIA) are used for the estimation of skeletal muscle mass (SMM) and lean body mass (LBM). No previous studies have examined whether these methods generate comparable results, or whether they are valid by using DXA as the reference. The aims of the present investigation were: (a) to assess the differences between DXA, anthropometry, and BIA in the estimation of SMM and LBM, taking into consideration the impact of sex and hydration status; and (b) to examine the agreement of anthropometry and BIA as compared to DXA for the estimation of SMM and LBM.MethodsA descriptive cross-sectional design was followed with 262 healthy young adults (159 males and 103 females). LBM and SMM were assessed by anthropometry with the formulas from Lee et al. and Kulkarni et al. for LBM; and Kerr (opt a), Kerr (opt b), Lee et al., Poortmans, Matiegka, Martin et al., Drinkwater and Ross, and Heymsfield et al. for SMM; by BIA with the formula reported by the TANITA MC-780-MA software for LBM and SMM; and DXA with the formula reported by the Hologic Horizon software for LBM, and the conversion by Kim et al. for SMM.ResultsSignificant differences were found for both SMM and LBM in kg, and percentages between most methods and formulas for the overall sample (p < 0.001-0.003) and divided by sex (p < 0.001-0.035). Hydration status did not have a significant effect on the differences between methods and formulas (p = 0.058-0.870). Lin's coefficient revealed limited agreement among the majority of formulas and methods (CCC = 0.007-0.880). The Bland-Altman analysis showed significant differences in most methods and formulas, both in the overall sample and divided by sex, when using SMM and LBM with DXA as the reference (p < 0.001-0.030).ConclusionThere is a lack of agreement between methods and formulas for assessing SMM and LBM. Sex was found to be a significant factor in this analysis. Furthermore, significant differences were observed between most formulas and methods as compared to DXA, except for the equations to estimate SMM with anthropometry by Poortmans.

Project description:Bioelectrical impedance analysis (BIA) is currently the most commonly used method in clinical practice to measure body composition. However, the bioelectrical impedance analyzer is not designed according to different countries, races, and elderly populations. Because different races may have different body compositions, a prediction model for the elderly population in Taiwan should be developed to avoid population bias, thereby improving the accuracy of community evaluation surveys.Dual energy X-ray absorptiometry (DXA) was used as a standard method for comparison, and impedance analysis was used for the development of a highly accurate predictive model that is suitable for assessing the body composition of elderly people.This study employed a cross-sectional design and recruited 438 elderly people who were undergoing health examinations at the health management center in the Tri-Service General Hospital as study subjects. Basic demographic variables and impedance analysis values were used in four predictive models, namely, linear regression, random forest, support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost) models, to predict DXA body composition. The data from 354 study subjects were used to develop the predictive model, while the data from 84 study subjects were used to validate the accuracy of the predictive model.The body composition of elderly people as estimated by InBody 720 was highly correlated with that estimated by DXA. The correlation coefficient between InBody 720 and DXA for muscle mass was 0.969, and that for fat mass was 0.935. Consistency analysis results showed that InBody 720 tends to underestimate muscle mass and fat mass. A comparison of the accuracy of the linear regression, random forest, SVM, and XGBoost models showed that the linear regression has the highest accuracy. The correlation coefficient between the new model and DXA for muscle mass and fat mass were 0.977 and 0.978, respectively.The new predictive model can be used to monitor the nutrition status of elderly people and identify people with sarcopenia in the community.

Dataset Information

Variable selection and importance in presence of high collinearity: an application to the prediction of lean body mass from multi-frequency bioelectrical impedance.

Publications

Variable selection and importance in presence of high collinearity: an application to the prediction of lean body mass from multi-frequency bioelectrical impedance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets