The association of dementia with upper arm and waist circumference in seven low- and middle-income countries: the 10/66 cross-sectional surveys

Abstract

Background: Weight loss in dementia contributes to morbidity and mortality but the distribution of anthropometric change and its consistency between populations are less clear. Our aim was to investigate and compare the associations of dementia with waist and upper arm circumference in elders from seven low- and middle-income nations.

Methods: Cross-sectional surveys were conducted of 15,022 residents aged 65 years and older in Cuba, Mexico, Venezuela, Peru, Dominican Republic, China, and India. Dementia was assessed using a cross-culturally validated algorithm, and anthropometric measurements were taken. Associations with dementia and dementia severity (clinical dementia rating scale) were investigated in linear regression models, with fixed-effects meta-analyses used to investigate between-country heterogeneity.

Results: Dementia and increased dementia severity were both associated with smaller arm and waist circumferences with little evidence of confounding by sociodemographic and health status. Associations between dementia/clinical dementia rating and arm circumference were homogeneous between countries (Higgins I(2) 0% and 7%, respectively), whereas those with waist circumference were more heterogeneous (Higgins I(2) 67% and 62%, respectively).

Conclusions: Although cross-sectional, our findings are consistent with prospective observations of weight loss in dementia and suggest loss of both muscle and fat-the former being consistent across different settings and the latter being more context dependent.

Figure 1.

Forest plot of country-specific estimates of difference in (A) arm circumference by dementia diagnosis based on Model 3 (adjusted for age, sex, education, assets, markers of chronic disease, and smoking) and pooled estimate from fixed-effect model meta-analysis (B) waist circumference by dementia diagnosis based on Model 3 (adjusted for age, sex, education, assets, markers of chronic disease, and smoking) and pooled estimate from fixed-effect model meta-analysis.

Figure 2.

Forest plot of country-specific estimates of association of (A) arm circumference with clinical dementia rating (CDR) based on Model 3 (adjusted for age, sex, education, assets, markers of chronic disease, and smoking) and pooled estimate from fixed-effect model meta-analysis (B) waist circumference with CDR based on Model 3 (adjusted for age, sex, education, assets, markers of chronic disease, and smoking) and pooled estimate from fixed-effect model meta-analysis.