Associations Between Different Dietary Vitamins and the Risk of Obesity in Children and Adolescents: A Machine Learning Approach

Abstract

BackgroundsSimultaneous dietary intake of vitamins is considered as a common and real scenario in daily life. However, limited prospective studies have evaluated the association between multivitamins intake and obesity in children and adolescents.ObjectivesThis study aimed to evaluate the relationship between the intake of different dietary vitamins and the risk of obesity in children (6-11 years) and adolescents (12-19 years).MethodsWe conducted a cross-sectional study based on data from U.S. National Health and Nutrition Examination Survey, 2013-2016. A total of 3634 children and adolescents were included who had available data on dietary vitamins, obesity and covariates. We analyzed the dietary intake levels of nine vitamins, including vitamin A, vitamin B1, vitamin B2, vitamin B6, vitamin B12, vitamin C, vitamin D, vitamin E, vitamin K. Multivariate logistic regression was used to model the associations between vitamins and obesity. Bayesian kernel machine regression (BKMR) was employed to explore the joint and independent effects of vitamins on obesity among children and adolescents.ResultsIn the multivariate logistic regression model, five vitamins (vitamin A, vitamin B1, vitamin B2, vitamin B12, and vitamin D) were negatively associated with obesity in children and adolescents. BKMR analysis showed that when the concentration of the nine vitamins was at or above the 55th percentile compared with the median value, the combined intake of these vitamins could significantly reduce the risk of obesity in children and adolescents. Potential interactions between vitamin B2 and vitamin B12 in increasing the risk of obesity in children and adolescents were observed.ConclusionsWe determine the combined effects of multivitamins on obesity in children and adolescents, and observe a significant interaction between vitamin B2 and vitamin B12. Further cohort studies are needed to clarify the health effects of multivitamins intake in a larger population.

Diet and Nutrients Intakes during Infancy and Childhood in Relation to Early Puberty: A Systematic Review and Meta-Analysis

“…The intermediate impact of obesity may be a feasible research direction. However, much of the literature concerning the relationship between vitamins and obesity was controversial or contradictory [ 78 , 79 ]. Lignan, one kind of phytochemical, is defined as phytoestrogen due to its estrogenic and antiestrogenic properties [ 80 , 81 ].…”

Dietary Inflammatory Nutrients and Esophageal Squamous Cell Carcinoma Risk: A Case-Control Study

“…Noteworthily, in addition to the explanation of the whole effects of all nutrients, this study based on the function of DII has the superiority in graphically and specifically revealing individual effects and mutual effects among nutrients that may be very important mechanistically. This implied that the relationship between dietary nutrients and ESCC may not be simply predicted by DII, and the exploration of the interaction and other effects of nutrients by BKMR can be used as a favorable supplement to DII so as to more holistically evaluate the association between inflammatory diets and ESCC [ 15 , 16 , 17 ].…”

“…This implicated the relationship between dietary nutrients and ESCC that might not be simply predicted by DII. The exploration of the interaction and other effects of nutrients by BKMR can be used as a favorable supplement to DII so as to more holistically evaluate the influence of inflammatory diets on ESCC and preliminarily provide causal inference clues for the follow-up mechanism research [ 15 , 16 , 17 ]. Consequently, this study aims to do the following: (1) investigate the association of multiple dietary nutrients’ (cataloged into pro- and anti-inflammation) co-exposure with ESCC risk; (2) evaluate the impact of single-effect and interaction within different inflammatory levels of nutrients on ESCC risk through implementing a BKMR model, providing preliminary causal inferences in diet-related carcinogenesis and a reference base for the nutritional prevention of ESCC.…”

Machine learning insights concerning inflammatory and liver-related risk comorbidities in non-communicable and viral diseases

“…ML algorithms have also elucidated the risk factors of childhood obesity, of which parental BMI and the upbringing environment play a huge role[ 80 - 82 ]. Furthermore, researchers have observed by training a multivariate LR model with a dataset of 3634 children and adolescents’ vitamin intake that vitamins A, D, B1, B2, and B12 were associated in a negative manner with obesity in this cohort[ 83 ]. These results are of interest since new insights are needed to discover novel targets to tackle comorbidities that affect liver function.…”