The different effects of neighbourhood and individual social capital on health-compromising behaviours in women during pregnancy: a multi-level analysis

Background: This study assessed clustering of three health-compromising behaviours and explored the association of neighbourhood and individual social capital with simultaneous health-compromising behaviours and patterns of those behaviours in women in the first trimester of pregnancy (baseline) and during the second and third trimesters of pregnancy (follow-up). Methods: A longitudinal study was conducted on a representative sample of women recruited in antenatal care units grouped in 46 neighbourhoods from Brazil. Neighbourhood-level measures (social capital and socioeconomic status), individual social capital (social support and social networks) and socio-demographic variables were collected at baseline. Smoking, alcohol consumption and inadequate diet were assessed at baseline and follow-up. Clustering was assessed using an observed to expected ratio method. The association of contextual and individual social capital with the health-compromising behaviours outcomes was analyzed through multilevel multivariate regression models. Results: Clustering of the three health-compromising behaviours as well as of smoking and alcohol consumption were identified at both baseline and follow-up periods. Neighbourhood social capital did not influence the occurrence of simultaneous health-compromising behaviours. More health-compromising behaviours in both periods was inversely associated with low levels of individual social capital. Low individual social capital predicted smoking during whole pregnancy, while high individual social capital increased the likelihood of stopping smoking and improving diet during pregnancy. Maintaining an inadequate diet during pregnancy was influenced by low individual and neighbourhood social capital. Conclusions: Three health-compromising behaviours are relatively common and cluster in Brazilian women throughout pregnancy. Low individual social capital significantly predicted simultaneous health-compromising behaviours and patterns of smoking and inadequate diet during pregnancy while low neighbourhood social capital was only relevant for inadequate diet. These findings suggest that interventions focusing on reducing multiple behaviours should be part of antenatal care throughout pregnancy. Individual and contextual social resources should be considered when planning the interventions.