Dataset Information

Waist circumference prediction for epidemiological research using gradient boosted trees

ABSTRACT:

Background

Waist circumference is becoming recognized as a useful predictor of health risks in clinical research. However, clinical datasets tend to lack this measurement and self-reported values tend to be inaccurate. Predicting waist circumference from standard physical features could be a viable method for generating this information when it is missing or mitigating the impact of inaccurate self-reports. This study determined the degree to which the XGBoost advanced machine learning algorithm could build models that predict waist circumference from height, weight, calculated Body Mass Index, age, race/ethnicity and sex, whether they perform better than current models based on linear regression, and the relative importance of each feature in this prediction.

Methods

We trained tree-based models (via XGBoost gradient boosting) and linear models (via regression) to predict waist circumference from height, weight, Body Mass Index, age, race/ethnicity and sex (n?=?60,740 participants). We created 10 iterations of each model, each using 90% of the dataset for training and the remaining 10% for testing performance (this group was different for each iteration). We calculated model performance and feature importance as an average across 10 iterations. We then externally validated the ensembled version of the top model.

Results

The XGBoost model predicted waist circumference with a mean bias ± standard deviation of 0.0?±?0.04?cm and a root mean squared error of 4.7?±?0.05?cm, with performance varying slightly by sex and race/ethnicity. The XGBoost model showed varying degrees of improvement over linear regression models. The top 3 predictors were Body Mass Index, weight and race (Asian). External validation found that on average this model overestimated waist circumference by 4.65?cm in the United Kingdom population (mainly due to overprediction in females) and underestimated waist circumference by 1.7?cm in the Chinese population. The respective root mean squared errors were 7.7?cm and 7.1?cm.

Conclusions

XGBoost-based models accurately predict waist circumference from standard physical features. Waist circumference prediction using this approach would be valuable for epidemiological research and beyond.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01242-9.

SUBMITTER: Zhou W

PROVIDER: S-EPMC7944598 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundClinical models to predict first trimester viability are traditionally based on multivariable logistic regression (LR) which is not directly interpretable for non-statistical experts like physicians. Furthermore, LR requires complete datasets and pre-established variables specifications. In this study, we leveraged the internal non-linearity, feature selection and missing values handling mechanisms of machine learning algorithms, along with a post-hoc interpretability strategy, as potential advantages over LR for clinical modeling.MethodsThe dataset included 1154 patients with 2377 individual scans and was obtained from a prospective observational cohort study conducted at a hospital in London, UK, from March 2014 to May 2019. The data were split into a training (70%) and a test set (30%). Parsimonious and complete multivariable models were developed from two algorithms to predict first trimester viability at 11-14 weeks gestational age (GA): LR and light gradient boosted machine (LGBM). Missing values were handled by multiple imputation where appropriate. The SHapley Additive exPlanations (SHAP) framework was applied to derive individual explanations of the models.ResultsThe parsimonious LGBM model had similar discriminative and calibration performance as the parsimonious LR (AUC 0.885 vs 0.860; calibration slope: 1.19 vs 1.18). The complete models did not outperform the parsimonious models. LGBM was robust to the presence of missing values and did not require multiple imputation unlike LR. Decision path plots and feature importance analysis revealed different algorithm behaviors despite similar predictive performance. The main driving variable from the LR model was the pre-specified interaction between fetal heart presence and mean sac diameter. The crown-rump length variable and a proxy variable reflecting the difference in GA between expected and observed GA were the two most important variables of LGBM. Finally, while variable interactions must be specified upfront with LR, several interactions were ranked by the SHAP framework among the most important features learned automatically by the LGBM algorithm.ConclusionsGradient boosted algorithms performed similarly to carefully crafted LR models in terms of discrimination and calibration for first trimester viability prediction. By handling multi-collinearity, missing values, feature selection and variable interactions internally, the gradient boosted trees algorithm, combined with SHAP, offers a serious alternative to traditional LR models.

Project description:BackgroundLittle is known about the long-term shifts in distributions of three abdominal-obesity-related indicators, waist circumference (WC), waist-to-hip ratio (WHpR) and waist-to-height ratio (WHtR) among Chinese adults. Traditional mean regression models used in the previous analyses were limited in their ability to capture cross-distribution among effects. The current study aims to describe the shift in distribution of WC, WHpR, and WHtR over a period of 18 years (1993-2011) in China, and to reveal quantile-specific associations of the three indicators with key covariates.MethodsLongitudinal data from seven waves of the China Health and Nutrition Surveys (CHNS) in 1993, 1997, 2000, 2004, 2006, 2009 and 2011 were analyzed. The LMS method was used to illustrate the gender-specific quantile curves of WC, WHtR and WHpR over age. Separate gender-stratified longitudinal quantile regressions were employed to investigate the effect of important factors on the trends of the three indicators.ResultsA total of 11,923 participants aged 18-65 years with 49,507 observations were included in the analysis. The density curves of WC, WHtR and WHpR shifted to right and became wider. The three outcomes all increased with age and increased more at upper percentiles. From the multivariate quantile regression, physical activity was negatively associated in both genders; smoking only had a negative effect on male indicators. Education and drinking behavior both had opposite effects on the three indicators between men and women. Marital status and income were positively associated with the shifts in WC, WHtR and WHpR in male and female WC, while urbanicity index had a positive effect on three outcomes in men but inconsistent effect among female outcomes.ConclusionsThe abdominal-obesity related indicators of the Chinese adults experienced rapid growth according to our population-based, age- and gender-specific analyses. Over the 18-year study period, major increases in WC, WHtR and WHpR were observed among Chinese adults. Specifically, these increases were greater at upper percentiles and in men. Age, physical activity, energy intake, drinking, smoking, education, income and urbanicity index were associated with elevated abdominal obesity indicators, and the effects differed among percentiles and between genders.