Characterisation and correlates of stunting among Malaysian children and adolescents aged 6-19 years

Abstract

Background: Despite emerging evidence regarding the reversibility of stunting at older ages, most stunting research continues to focus on children below 5 years of age. We aimed to assess stunting prevalence and examine the sociodemographic distribution of stunting risk among older children and adolescents in a Malaysian population.

Methods: We used cross-sectional data on 6759 children and adolescents aged 6-19 years living in Segamat, Malaysia. We compared prevalence estimates for stunting defined using the Centers for Disease Control and Prevention (CDC) and the World Health Organization (WHO) references, using Cohen's κ coefficient. Associations between sociodemographic indices and stunting risk were examined using mixed-effects Poisson regression with robust standard errors.

Results: The classification of children and adolescents as stunted or normal height differed considerably between the two references (CDC v. WHO; κ for agreement: 0.73), but prevalence of stunting was high regardless of reference (crude prevalence: CDC 29.2%; WHO: 19.1%). Stunting risk was approximately 19% higher among underweight v. normal weight children and adolescents (p = 0.030) and 21% lower among overweight children and adolescents (p = 0.001), and decreased strongly with improved household drinking water sources [risk ratio (RR) for water piped into house: 0.35, 95% confidence interval (95% CI) 0.30-0.41, p < 0.001). Protective effects were also observed for improved sanitation facilities (RR for flush toilet: 0.41, 95% CI 0.19-0.88, p = 0.023). Associations were not materially affected in multiple sensitivity analyses.

Conclusions: Our findings justify a framework for strategies addressing stunting across childhood, and highlight the need for consensus on a single definition of stunting in older children and adolescents to streamline monitoring efforts.

Keywords: Child nutrition; South East Asia; child stunting; health and demographic surveillance; water and sanitation.

Fig. 1.

Association of stunting with selected individual, parental and household water and sanitation indices – stunting expressed using the (a) Centers for Disease Control and Prevention 2000 reference and (b) World Health Organization 2007 reference. Estimates presented from Poisson regression models described in online Supplementary Tables S5 and S10. RR, risk ratio; 95% CI, 95% confidence interval (error bars). Flush toilet includes that connected with septic tank or sewerage system; unprotected drinking water sources: unprotected dug well, or water taken directly from pond or stream; protected sources: public standpipe, protected dug well or spring, or water from bottles or tanker truck.

Fig. 2.

Summary of effect of sensitivity analyses on associations between key indices and stunting risk. (a) Original regression model (online Supplementary Table S5; N = 3791); (b) model with maternal age included (N = 3337); (c) model with maternal education included (N = 3625); (d) model with paternal height included (N = 2723); (e) model with orthogonal variables included (N = 3434). RR, risk ratio; 95% CI, 95% confidence interval (error bars); BMI, body mass index. Stunting and BMI-for-age were defined using the Centers for Disease Control and Prevention 2000 reference. Flush toilet includes that connected with septic tank or sewerage system; unprotected drinking water sources: unprotected dug well, or water taken directly from pond or stream; protected sources: public standpipe, protected dug well or spring, or water from bottles or tanker truck. Orthogonal variables: maternal heart rate, maternal diastolic blood pressure, household Streamyx Internet and motorcycles per household member.

Fig. 3.

Relative risk of stunting associated with the number of co-occurring risk factors. Stunting was classified using the Centers for Disease Control and Prevention 2000 reference. Dashed line represents null association (relative risk of 1); error bars denote 95% confidence interval. Risk factors included: Malay ethnicity, child underweight, maternal height <145 cm, living in a household with unprotected drinking water source (unprotected dug well, or water taken directly from pond or stream), living in household with no bucket or hanging latrine and living in a household with a shared toilet. Estimates are based on Poisson regression models adjusted for the child's age, sex and body mass index-for-age status, birth order, maternal current underweight, rooms per household member, household's main method of garbage disposal and for clustering at the household level.