Socio-economic disparities in child-to-adolescent growth trajectories in China: Findings from the China Health and Nutrition Survey 1991-2015

Abstract

Backgrounds: Socio-economic disparities in growth trajectories of children from low-/middle-income countries are poorly understood, especially those experiencing rapid economic growth. We investigated socio-economic disparities in child growth in recent decades in China.

Methods: Using longitudinal data on 5095 children/adolescents (7-18 years) from the China Health and Nutrition Survey (1991-2015), we estimated mean height and BMI trajectories by socio-economic position (SEP) and sex for cohorts born in 1981-85, 1986-90, 1991-95, 1996-2000, using random-effects models. We estimated differences between high (urbanization index ≥median, household income per capita ≥median, parental education ≥high school, or occupational classes I-IV) and low SEP groups.

Findings: Mean height and BMI trajectories have shifted upwards across cohorts. In all cohorts, growth trajectories for high SEP groups were above those for low SEP groups across SEP indicators. For height, socio-economic differences persisted across cohorts (e.g. 3.8cm and 2.9cm in earliest and latest cohorts by urbanization index for boys at 10 year, and 3.6cm and 3.1cm respectively by household income). For BMI, trends were greater in high than low SEP groups, thus socio-economic differences increased across cohorts (e.g. 0.5 to 0.8kg/m² by urbanization index, 0.4 to 1.1kg/m² by household income for boys at 10 year). Similar trends were found for stunting and overweight/obesity by SEP. There was no association between SEP indicators and thinness.

Interpretation: Socio-economic disparities in physical growth persist among Chinese youth. Short stature was associated with lower SEP, but high BMI with higher SEP. Public health interventions should be tailored by SEP, in order to improve children's growth while reducing overweight/obesity.

Funding: MG is supported by UCL Overseas Research Scholarship and China Scholarship Council for her PhD study. WJ is supported by a UK Medical Research Council (MRC) New Investigator Research Grant (MR/P023347/1) and acknowledges support from the National Institute for Health Research (NIHR) Leicester Biomedical Research Centre, which is a partnership between University Hospitals of Leicester NHS Trust, Loughborough University, and the University of Leicester.

Keywords: BAZ, BMI-for-age z-scores; BMI trajectories; BMI, Body mass index; CHNS, China Health and Nutrition Survey; Changes over time; Chinese children and adolescents; HAZ, height-for-age z-scores; HICs, high-income countries; Height trajectories; LMICs, low-/middle-income countries; SEP, socio-economic position; Socio-economic disparities.

Figure 1

Mean (95%CI) height and BMI z-scores (HAZ and BAZ)^§ by SEP groups^† and SEP differences (high – low) in z-scores across cohorts^‡ Note: 1981–85: earliest cohort, 1996–2000: latest cohort. Abbreviations: HH: household; SEP: socio-economic position; CI: confidence interval. ^§HAZ and BAZ were height-for-age and BMI-for-age z-scores using sex- and age-specific WHO 2007 growth reference. ^†High/low SEP groups: urbanization Index and HH income per capita: ≥/< cohort-specific median. Educational level: ≥ High/≤ Middle school. Occupational class: class I-IV /V. ^‡All values were estimated from 2-level linear models for height and BMI z-scores (level-1: measurement; level-2: individual).

Figure 2

Mean height (95%CI) trajectories by SEP groups* for the earliest & latest cohorts (left y-axis) and differences in mean height between high and low SEP groups (right y-axis) across cohorts for (A) boys and (B) girls^† Note: 1981–85: earliest cohort, 1996–2000: latest cohort. Abbreviations: HH: household; SEP: socio-economic position; CI: confidence interval. *High/low SEP group: urbanization Index and HH income per capita: ≥/< cohort-specific median. Educational level: ≥ High/†All values were estimated from 2-level fractional polynomial models (level-1: measurement; level-2: individual).

Figure 3

Mean BMI (95%CI) trajectories by SEP groups* for the earliest & latest cohorts (left y-axis) and differences in mean BMI between high and low SEP groups (right y-axis) across cohorts for (A) boys and (B) girls^† Note: 1981–85: earliest cohort, 1996–2000: latest cohort. Abbreviations: HH: household; SEP: socio-economic position; CI: confidence interval. *High/low SEP group: urbanization Index and HH income per capita: ≥/< cohort-specific median. Educational level: ≥ High/†All values were estimated from 2-level fractional polynomial models (level-1: measurement; level-2: individual).

Figure 4

Prevalence (95%CI) of stunting, thinness and overweight/obesity § by SEP groups (solid lines) * and their ORs (high vs low SEP, dash lines) across cohorts^† Note: 1981–85: earliest cohort, 1996–2000: latest cohort. Abbreviations: HH: household; SEP: socio-economic position; OR: odds ratio; CI: confidence interval. ^§Stunting, thinness and overweight were defined by WHO 2007 reference. * High/low SEP groups: urbanization Index and HH income per capita: ≥/< cohort-specific median. Educational level: ≥ High/≤ Middle school. Occupational class: class I-IV /V. ^†All values estimated for boys aged 10 year from 2-level (level-1: measurement; level-2: individual) logistic models with adjustment for age and sex.