Associations between children's diets and features of their residential and school neighbourhood food environments.

Van Hulst, Andraea ; Barnett, Tracie A. ; Gauvin, Lise 等

In recent years, the role of neighbourhoods has been increasingly investigated with respect to obesity in children. (1-3) Neighbourhood built environments may promote childhood obesity by favouring antecedent behaviours, including physical inactivity and unhealthful diets. Compared with physical activity, fewer studies have addressed children's diets. (1)

Most studies examining associations between local neighbourhood availability of food establishments and residents' diets have focused on adults. (4) Overall, findings from studies involving children are less consistent, notably for associations between access to supermarkets and vegetable and fruit (V&F) intake. (5-7) Greater access to convenience stores, which typically offer limited fresh produce, has been found to be associated with lower V&F intake5, (7) and higher intake of sweet/salty snacks6 and sugar-sweetened beverages (8) in youth. Although some studies have reported associations between the availability of fast-food restaurants near children's residence and their diets, (7,8) others do not support such findings. (6,9,10) Given the conflicting results in the literature, there is a need to clarify the relation between neighbourhood food environments and children's diets.

In addition to residential neighbourhoods, school neighbourhood environments are relevant activity spaces and should be investigated in relation to obesity-related behaviours in children. (11,12) During the academic year, travel to and from school exposes children to school neighbourhood food environments. Recently, policies have targeted in-school food environments, but initiatives aimed at regulating food opportunities in school neighbourhoods have yet to be widely implemented. Fast-food restaurants and convenience stores are known to cluster within short distances from schools.13,14 However, it is not clear to what extent the availability of the latter is associated with children's diet. (2,9)

The aim of this study was to determine whether features of residential and school neighbourhood food environments were associated with children's dietary intake (V&F and sugar-sweetened beverages) and selected dietary behaviours (eating/snacking out and consuming delivered/take-out food).

METHODS

Participants were drawn from the QUALITY (Quebec Adipose and Lifestyle Investigation in Youth) study, an ongoing longitudinal investigation of the natural history of obesity and cardiovascular risk in youth with a history of parental obesity. Recruitment flyers were distributed to parents of children in Grades 2 to 5 in 1,040 primary schools (89% of schools approached) located within 75 km of each of Montreal, Quebec City and Sherbrooke, QC. Of 3,350 interested families who contacted the research coordinator, 1,320 met the study inclusion criteria. Eligibility criteria required participating children to be Caucasian, aged 8-10 years at recruitment and to have at least one obese biological parent (i.e., body mass index [BMI] [greater than or equal to] 30 kg/[m.sup.2] and/or waist circumference >102 cm in men and >88 cm in women, based on self-reported measurements of height, weight and waist circumference) and both biological parents available to participate at baseline. Of eligible families, a total of 630 (48% of eligible families composed of the participating child and two biological parents) completed the baseline visit between September 2005 and December 2008. Baseline data collection involved a clinic visit during which questionnaires were completed and biological and physiological measurements obtained, as well as follow-up telephone interviews. Written informed consent was obtained from parents, and assent was provided by children. The ethics review boards of Centre Hospitalier Universitaire SainteJustine and Laval University approved the study. A detailed description of the study design and methods is available elsewhere. (15)

Characteristics of the built and social environments in children's residential neighbourhood were obtained for the study baseline using a Geographic Information System (GIS) for 512 children residing in the Montreal Census Metropolitan Area (CMA). Of these, 506 attended some 296 schools located within the Montreal CMA, for which school neighbourhood GIS data were also obtained.

Dietary assessment

Children's dietary intake was measured using mean values of three 24-hour diet recalls conducted by trained dieticians on nonconsecutive days, including one weekend day. (16) Data from recalls were available for 498 participants considered in this study. Except in unusual circumstances, the recalls were collected within a 4-week period after the baseline clinic visit. Diet recall interviews were done by telephone with the child and then confirmed with the parent who prepared the meals.

Foods reported on the recalls were entered into CANDAT (London, ON) and converted to nutrients using the 2007b Canadian Nutrient File. (17) Daily servings of V&F were based on portion sizes from Canada's Food Guide and include V&F juices. A dichotomous variable was developed on the basis of recommended servings of V&F for children aged 8-10 years: [greater than or equal to] 5 servings/day vs. less. (18) Intake of sugar-sweetened beverages was computed as the mean daily number of millilitres of soft drinks and other sugar-sweetened drinks, but excluding juices made from real fruits. Given a substantial positive skewness in its distribution, sugar-sweetened beverage intake was dichotomized to >50 mL/day (approximately one can of soft drink per week) vs. less.

Two additional measures of children's diets were obtained from a questionnaire administered to the child during the clinic visit: having a meal or snack in a food establishment at least once in the previous week and consuming delivered or "take-out" food at least once in the previous week.

Neighbourhood assessment

The exact addresses of each participating child's residence and school were geocoded. The availability of food establishments within the residential and school neighbourhood environment was measured using a GIS, which included data from an exhaustive list, acquired from Tamec Inc., of businesses and services located in the region in May 2005. The business name, address, postal code and Standard Industry Classification code were available. A validity study of food establishments from this list, verified by onsite field visits, showed good agreement (0.77), sensitivity (0.84) and positive predictive value (0.90). (19) All businesses were geocoded using GeoPinPoint[TM], version 2007.3 (DMTI Spatial Inc.). Types of food establishment included in this study were supermarkets, fast-food restaurants, (14) convenience stores and specialty food stores (e.g., bakeries, fruit and vegetables, gourmet, meat and fish markets).

Neighbourhood food environments were described by proximity- and density-based indicators. Proximity measures were established using ArcGIS Network Analyst (Esri, Redlands, CA) and defined as the road-network distance between the child's residence and the nearest supermarket, fast-food restaurant and convenience store, and between the child's school and the nearest of each food establishment type. Because of highly skewed distributions, indicators were categorized into tertiles corresponding to farthest, intermediate and shortest distances. Kernel density was used to estimate the average density of each type of food establishment within 1 km street network buffers centred on 1) the child's residence and 2) the child's school. Kernel density estimations are frequently used in geography to evaluate the local density of point-based data (20) and have been used previously to describe neighbourhood access to food establishments. (21) A quartic kernel function was used with adaptive bandwidth composed of 1% of the observations for each type of food establishment (n=1,929 for convenience stores, n=1,118 for fast-food restaurants and n=828 for supermarkets) and cell spacing of 100 m. Exposure categories for each type of food establishment were based on tertiles corresponding to lowest, intermediate and highest densities.

Additionally, a Retail Food Environment Index (RFEI) was computed. (22) This index is based on the ratio of the number of fast-food restaurants and convenience stores to supermarkets and specialty food stores. Higher scores are indicative of neighbourhoods characterized by a higher number of unhealthful relative to healthful options. The RFEI was computed for 1 km network buffers and for 3 km radius circular buffers centred on each of the residential and school locations. A larger buffer was examined to capture greater variation among neighbourhoods in RFE indices. The index was subsequently categorized according to the approximate 75th percentile of each variable's distribution, corresponding to cut-offs of [greater than or equal to] 2.0 vs. less for 1 km buffers and [greater than or equal to] 2.5 vs. less for 3 km buffers.

Other neighbourhood-level measures included a material deprivation index computed from 2006 Census data.23 The index combines the proportion of people with no high school diploma, the proportion who are employed and the average income, for people aged [greater than or equal to] 15 years in census dissemination areas. Population-weighted proportions of dissemination areas overlapping 1 km street network buffers centred on resident's location were computed. The index was classified into quintiles of lowest to highest deprivation. A material deprivation index for school neighbourhood was computed using the same approach. Population density for both residential and school neighbourhood environments was computed from 2006 Census data for 1 km street network buffers. A median split categorization was used for measures of population density.

Individual socio-demographic measures

Individual-level data used as adjustment variables included child's age and sex, and mother's BMI. Highest parental educational attainment (2 parents with secondary school or less, [greater than or equal to] 1 parent with technical/vocational/trade degree, [greater than or equal to] 1 parent with university degree) and total annual household income adjusted for the number of people living in the household were obtained from parent-completed questionnaires during the clinic visit.

Analysis

This study was not designed to allow multilevel analyses of participants nested into neighbourhoods; instead, an ego-centred approach was used whereby individual neighbourhood measures were computed for each child's residential and school locations. (24) Moreover, no evidence of spatial autocorrelation resulting from the dependency of properties within geographic spaces was found, indicating that nearby entities did not share more similarities than entities that were further apart (data not shown).

Unadjusted associations among indicators of residential neighbourhood food environment and dietary outcomes were examined using logistic regression. Subsequently, multivariable associations were analyzed adjusting for child's age and sex, as well as for potential confounders, namely parental education, household income, residential neighbourhood material deprivation and residential population density (as a measure of level of urbanicity). For analyses involving school neighbourhoods, generalized estimating equations (GEE) with a logit link function and with an independent working correlation structure were used to allow for clustering of dietary outcomes among children attending the same schools. Multivariable GEE models were adjusted for child's age, sex, parental education, household income, school neighbourhood material deprivation and school neighbourhood population density. Given the high correlations between proximity-based indicators and between density-based indicators of each type of food establishment (r=0.7 to 0.9), each variable was examined in separate models for residential and school neighbourhoods using the "best access" (i.e., closest or densest tertile) as the reference category. For RFE indices, values below the cut-offs were used as the reference category. Odds ratios (OR) and 95% confidence intervals (CIs) are presented. All analyses were conducted using SAS, version 9.2 (Cary, NC).

In secondary analyses, we restricted the sample to children who lived >1.5 km from their school, i.e., those who were more likely to have distinct residential and school neighbourhood food environments, since there would be minimal overlap between respective 1 km network buffers centred on each location. Associations between the density of food establishments and dietary outcomes were examined in this subgroup in an attempt explore which of the residential or school neighbourhood food environment features were most strongly associated with dietary outcomes.

RESULTS

Overall, 34% of the 512 children consumed the recommended daily intake of [greater than or equal to] 5 servings of V&F per day (average of 4.3 servings), 58% drank >50 mL of sugar-sweetened beverages daily, 44% had a meal/snack in a food establishment, and 35% consumed delivered/take-out foods at least once per week (Table 1). Overall, supermarkets, fast-food restaurants and convenience stores were more accessible around schools than around residences, as shown by shorter distances to and higher densities of each type of food establishment in school neighbourhoods. Thirty-eight percent (n=193) lived >1.5 km from their school.

Tables 2 and 3 show covariate-adjusted associations of proximity, density and retail food environment measures with children's dietary outcomes for both residential and school neighbourhood environments respectively. Living in a residential neighbourhood with a lower density of fast-food restaurants was associated with a 48% (OR=0.52, 95% CI: 0.30-0.91) and 40% (OR=0.60, 95% CI: 0.36-0.99) lower likelihood of eating/snacking out, for lowest and intermediate densities respectively. Similar associations were found for convenience stores, the lowest density compared with the highest density indicating a 56% (OR=0.44, 95% CI: 0.25-0.80) lower likelihood of eating/snacking out. Residential neighbourhood proximity-based indicators were not associated with children's diets, nor were residential RFE indices. Access to food establishments in the school environment was only marginally associated with dietary outcomes (Table 3). For example, intermediate (vs. shortest) distance between attended school and the nearest fast-food restaurant was associated with an increased likelihood of consuming recommended servings of V&F (p=0.08). Similarly, attending schools in neighbourhoods with the lowest density of supermarkets (vs. highest density) was associated with a decreased likelihood of eating/snacking out (p=0.08); an intermediate density of supermarkets (vs. highest density) was associated with an increased likelihood of consuming sugar-sweetened beverages (p=0.07); and intermediate density of fast-food restaurants (vs. highest density) was associated with an increased likelihood of consuming delivered/take-out foods (p=0.09).

The residential neighbourhood RFE indices were not associated with dietary outcomes (Table 2). Attending a school in a neighbourhood with a 3 km buffer RFE Index [greater than or equal to] 2.5 (i.e., 2.5 fast-food restaurants/convenience stores for 1 supermarket/specialty store) was associated with a 61% (OR=1.61, 95% CI: 1.01-2.56) greater likelihood of consuming sugar-sweetened beverages, after adjustment for individual and neighbourhood covariates (Table 3). Similarly, an elevated RFEI within 1 and 3 km buffers around schools was marginally associated with a lower likelihood of consuming recommended servings of V&F.

Among children living >1.5 km from their school, lowest (vs. highest) school neighbourhood density of fast-food restaurants was associated with a higher likelihood of consuming recommended servings of V&F, and intermediate (vs. highest) school neighbourhood density of fast-food restaurants was associated with a higher likelihood of consuming delivered/take-out food (Table 4). The residential density of convenience stores remained positively associated with eating/snacking out.

Last, when V&F intake was treated as a continuous variable using linear regression models, children living farthest from fast-food restaurants had a 0.5 additional serving of V&F daily ([beta]=0.50, 95% CI: 0, 1.00) compared with those living at the shortest distance. Moreover, living in or attending a school in a neighbourhood with 3 km RFE indices [greater than or equal to] 2.5 was associated with up to a half serving less of V&F ([beta]=-0.40, 95% CI: -0.81, 0.005 for residential neighbourhood and [beta]=-0.50, 95% CI: -0.91, -0.09 for school neighbourhood).

DISCUSSION

We examined associations between indicators of neighbourhood food environments and dietary outcomes among children with a family history of obesity. The findings suggest that the availability of fast-food restaurants and convenience stores in children's neighbourhood environments may be associated with their intake of V&F, and the likelihood of eating/snacking out and consuming delivered/take-out foods. This extends recent research on built environments and children's diets. Although associations tended to be weak in magnitude, observed associations are overall consistent with current research on obesogenic environments and health.

As previously reported, (5-7) we found no consistent associations between a greater availability of supermarkets and more favourable dietary outcomes. Supermarkets typically offer a large variety of healthful foods, including vegetables and fruits, at lower costs. (25) However, there appear to be very few "food deserts" in Montreal, i.e., neighbourhoods where residents are considered to have poor access to supermarkets. (26) Associations between the availability of supermarkets and diets may be more likely to emerge in areas with less equitable distributions of supermarkets and may be more relevant to adult populations. In contrast to supermarket availability, we found more evidence that the availability of fast-food restaurants and convenience stores was associated with children's diets, particularly with the likelihood of eating or having a snack in a food establishment. These findings suggest that easy access to unhealthful foods may be more of a concern than poor access to more healthful foods. (27)

Geographic clustering of fast-food restaurants and convenience stores around schools has been described previously, (14) although our findings suggest that associations between access to these food establishments and children's diets were more consistent for residential than for school neighbourhood exposures. This may be related to the relatively young age of participants; school neighbourhoods may become more important during adolescence, when students attending secondary school are typically authorized to leave school grounds. (28)

Use of the RFE indices revealed that children residing in or attending a school in neighbourhoods with a preponderance of unhealthful food establishments scored most poorly on dietary outcomes. (29) An indicator of relative access to types of food establishments is a useful complement to proximity- and density-based indicators, as commercial destinations tend to be geographically clustered such that higher numbers of fast-food restaurants are often associated with more supermarkets and fruit and vegetable stores as well.

Restricting analyses to the subgroup of children living >1.5 km from their school allowed us to partially distinguish associations with residential neighbourhood environments from associations with school neighbourhood environments. However, the results of these subanalyses are likely not generalizable to the entire sample. In this subgroup, children who lived farther away from their school were more likely to be driven to or from their school than to travel by bus. A higher likelihood of car travel may lead to more opportunistic purchases by parents, including those at drive-through restaurants, given the extended potential path area. (9,30) This may, in part, explain the higher fast-food intake among children living farther away from fast-food restaurants.

Initiatives to create zones around schools with limited access to fast-food restaurants and convenience stores have been proposed.31 Such initiatives may have a positive impact on children's diet, particularly in the context of ecological interventions in which multiple levels of obesogenic environments are targeted. Although school neighbourhoods might be more compelling targets, policies to limit access to unhealthful food establishments in residential neighbourhoods should be further investigated.

The strengths of this study include the use of a valid and reliable method to measure children's diet and the use of objective measures to characterize neighbourhood food environments. Overall, the findings should be interpreted with caution, given the number of associations tested and the increased risk of type-1 error. The results should thus be seen as exploratory and in need of confirmation in future studies. Other limitations include the possibility that children with certain dietary patterns were self-selected through their parents to reside in neighbourhoods with particular food establishment profiles. Moreover, because the majority of children lived within a short walking distance of their school, it was not possible to distinguish entirely between the associations of residential vs. school neighbourhood environments with children's diets. While we used a GIS to quantify the availability of various types of food establishment, (32) others have used measures of perceived access. (33) Parents and children may incorporate aspects other than local availability to formulate perceptions of access, such as car ownership, parental permissiveness and available pocket money; this should be examined in future research that includes both GIS and perceived measures. Last, since the children in this study were relatively young (8-10 years), associations of interest may be mediated and/or confounded by parental diet; however, there were no measures of parent diet in the QUALITY study. Maternal BMI was considered as a proxy for mother's diet, but was not retained because its inclusion in the models did not change main exposure coefficients substantively and because the study design required at least one parent to be obese.

In conclusion, our findings suggest that among children aged 8-10 years, residential neighbourhood food environments are more strongly associated with dietary outcomes than are school neighbourhood food environments. Although the magnitude of associations is relatively small, the potential to affect population dietary behaviours and related health outcomes may be substantial. Frequent and widespread food purchasing opportunities within children's environments may be one factor amenable to interventions to improve diets.

Acknowledgements: The QUALITY study is funded by the Canadian Institutes of Health Research (CIHR), the Heart and Stroke Foundation of Canada (HSFC) and the Fonds de la recherche en sante du Quebec. The QUALITY Residential and School Built Environment complementary studies were funded by the HFSC and the CIHR, respectively. A.Van Hulst received support from a CIHR/HSFC Training Grant in Population Intervention for Chronic Disease Prevention, and a doctoral scholarship from the Fonds de la recherche en sante du Quebec; T. Barnett and Y. Kestens are research scholars with Fonds de la recherche en sante du Quebec; L. Gauvin holds a CIHR/Centre de Recherche en Prevention de l'Obesite Chair in Applied Public Health on Neighbourhoods, Lifestyle, and Healthy Body Weight; and M. Bird received a Masters' scholarship from the Fondation du CHU Sainte-Justine. Dr. Marie Lambert passed away on February 20, 2012. Her leadership and devotion to the QUALITY cohort will always be remembered and appreciated.

Conflict of Interest: None to declare.

REFERENCES

(1.) Galvez MP, Pearl M, Yen IH. Childhood obesity and the built environment: A review of the literature from 2008-2009. Curr Opin Pediatr 2010;22(2):202 7.

(2.) Rahman T, Cushing RA, Jackson RJ. Contributions of built environment to childhood obesity. Mt Sinai J Med 2011;78(1):49-57.

(3.) Dunton GF, Kaplan J, Wolch J, Jerrett M, Reynolds KD. Physical environmental correlates of childhood obesity: A systematic review. Obes Rev

2009;10(4):393-402.

(4.) Larson NI, Story MT, Nelson MC. Neighborhood environments. Disparities in access to healthy foods in the U.S. Am J Prev Med 2009;36(1):74-81.

(5.) Pearce J, Hiscock R, Blakely T, Witten K. The contextual effects of neighbourhood access to supermarkets and convenience stores on individual fruit and vegetable consumption. J Epidemiol Community Health 2008;62(3):198-201.

(6.) Skidmore P, Welch A, van Sluijs E, Jones A, Harvey I, Harrison F, et al. Impact of neighbourhood food environment on food consumption in children aged 9-10 years in the UK SPEEDY (Sport, Physical Activity and Eating behaviour: Environmental Determinants in Young people) study. Public Health Nutr 2010;13(7):1022-30.

(7.) Timperio A, Ball K, Roberts R, Campbell K, Andrianopoulos N, Crawford D. Children's fruit and vegetable intake: Associations with the neighbourhood food environment. Prev Med 2008;46(4):331-35.

(8.) Jennings A, Welch A, Jones AP, Harrison F, Bentham G, van Sluijs EM, et al. Local food outlets, weight status, and dietary intake: Associations in children aged 9-10 years. Am J Prev Med 2011;40(4):405-10.

(9.) Timperio AF, Ball K, Roberts R, Andrianopoulos N, Crawford D. Children's takeaway and fast-food intakes: Associations with the neighbourhood food environment. Public Health Nutr 2009;12(10):1960-64.

(10.) An R, Sturm R. School and residential neighborhood food environment and diet among California youth. Am J Prev Med 2012;42(2):129-35.

(11.) Casey R, Oppert J-M, Weber C, Charreire H, Salze P, Badariotti D, et al. Determinants of childhood obesity: What can we learn from built environment studies? Food Quality and Preference 2011: doi:10.1016/j.foodqual.2011.06.003.

(12.) Papas MA, Alberg AJ, Ewing R, Helzlsouer KJ, Gary TL, Klassen AC. The built environment and obesity. Epidemiol Rev 2007;29:129-43.

(13.) Gebauer H, Laska MN. Convenience stores surrounding urban schools: An assessment of healthy food availability, advertising, and product placement. J Urban Health 2011;88(4):616-22.

(14.) Kestens Y, Daniel M. Social inequalities in food exposure around schools in an urban area. Am J Prev Med 2010;39(1):33-40.

(15.) Lambert M, van Hulst A, O'Loughlin J, Tremblay A, Barnett TA, Charron H, et al. The Quebec Adipose and Lifestyle Investigation in Youth (QUALITY) cohort. Int J Epidemiol 2011;Epub July 23.

(16.) Johnson RK, Driscoll P, Goran MI. Comparison of multiple-pass 24-hour recall estimates of energy intake with total energy expenditure determined by doubly labeled water method in young children. J Am Diet Assoc 1996;96(11):1140-44.

(17.) Health Canada. Canadian Nutrient File. Available at: http://www.hc-sc.gc.ca/fnan/nutrition/fiche-nutri-data/cnf_downloads-telechargement_fcen-eng.php (Accessed November 15, 2011).

(18.) Health Canada. Eating Well with Canada's Food Guide. A Resource for Educators and Communicators. Available at: http://www.hc-sc.gc.ca/fn-an/foodguide-aliment/index-eng.php (Accessed November 15, 2011).

(19.) Paquet C, Daniel M, Kestens Y, Leger K, Gauvin L. Field validation of listings of food stores and commercial physical activity establishments from secondary data. Int J Behav Nutr Phys Act 2008;5:58.

(20.) Carlos HA, Shi X, Sargent J, Tanski S, Berke EM. Density estimation and adaptive bandwidths: A primer for public health practitioners. Int J Health Geogr 2010;9:39.

(21.) Lebel A, Kestens Y, Pampalon R, Theriault M, Daniel M, Subramanian SV. Local context influence, activity space, and foodscape exposure in two Canadian metropolitan settings: Is daily mobility exposure associated with overweight? J Obes 2012;2012:ID 912645. Epub 2011 Dec 28.

(22.) Spence JC, Cutumisu N, Edwards J, Raine KD, Smoyer-Tomic K. Relation between local food environments and obesity among adults. BMC Public Health 2009;9:192.

(23.) Pampalon R, Hamel D, Gamache P, Raymond G. A deprivation index for health planning in Canada. Chronic Dis Can 2009;29(4):178-91.

(24.) Chaix B, Merlo J, Evans D, Leal C, Havard S. Neighbourhoods in ecoepidemiologic research: Delimiting personal exposure areas. A response to Riva, Gauvin, Apparicio and Brodeur. Soc Sci Med 2009;69(9):1306-10.

(25.) Diez Roux AV, Mair C. Neighborhoods and health. Ann N Y Acad Sci 2010;1186:125-45.

(26.) Apparicio P, Cloutier M-S, Shearmur R. The case of Montreal's missing food deserts: Evaluation of accessibility to food supermarkets. Int J Health Geogr 2007;6(4).

(27.) Hackett A, Boddy L, Boothby J, Dummer TJB, Johnson B, Stratton G. Mapping dietary habits may provide clues about the factors that determine food choice. J Hum Nutr Diet 2008;21(5):428-37.

(28.) Laska MN, Hearst MO, Forsyth A, Pasch KE, Lytle L. Neighbourhood food environments: Are they associated with adolescent dietary intake, food purchases and weight status? Public Health Nutr 2010;13(11):1757-63.

(29.) Babey SH, Wolstein J, Diamant A. Food environments near home and school related to consumption of soda and fast food. Los Angeles, CA: UCLA Center for Health Policy Research, 2011.

(30.) Paez A, Gertes Mercado R, Farber S, Morency C, Roorda M. Relative accessibility deprivation indicators for urban settings: Definitions and application to food deserts in Montreal. Urban Studies 2012;47(7):1415-38.

(31.) Association pour la sante publique du Quebec. The school zone and nutrition: Courses of action for the municipal sector. Available at: http://www.aspq.org/documents/file/guide-zonage-version-finale-anglaise.pdf (Accessed November 15, 2011).

(32.) Charreire H, Casey R, Salze P, Simon C, Chaix B, Banos A, et al. Measuring the food environment using geographical information systems: A methodological review. Public Health Nutr 2010;13(11):1773-85.

(33.) Veugelers P, Sithole F, Zhang S, Muhajarine N. Neighborhood characteristics in relation to diet, physical activity and overweight of Canadian children. Int J Pediatr Obes 2008;3(3):152-59.

Andraea Van Hulst, RN, MSc, [1,2] Tracie A. Barnett, PhD, [1,2] Lise Gauvin, PhD, [1,3,4] Mark Daniel, PhD, [1,5,6] Yan Kestens, PhD, [1,3] Madeleine Bird, BA, [1, 2] Katherine Gray-Donald, PhD, [7] Marie Lambert, MD [2,8]

La traduction du resume se trouve a la fin de l'article. Can J Public Health 2012;103(Suppl. 3):S48-S54.

Author Affiliations

[1.] Departement de medecine sociale et preventive, Universite de Montreal, Montreal, QC

[2.] Centre de recherche du Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC

[3.] Centre de Recherche du Centre Hospitalier de l'Universite de Montreal, Montreal, QC

[4.] Centre de Recherche Lea-Roback sur les Inegalites Sociales de Sante de Montreal, Universite de Montreal, Montreal, QC

[5.] School of Health Sciences, University of South Australia, Adelaide, Australia

[6.] Department of Medicine, St Vincent's Hospital, The University of Melbourne, Melbourne, Australia

[7.] School of Dietetics and Human Nutrition, McGill University, Montreal, QC

[8.] Departement de pediatrie, Universite de Montreal, Montreal, QC

Correspondence: Andraea Van Hulst, Centre de recherche du CHU Sainte-Justine, 5757 Ave. Decelles, suite 100, Montreal, QC H3S 2C3, Tel: 514-345-4931 (ext. 3271), Fax: 514-345-4801, E-mail: a.van.hulst@umontreal.ca Table 1. Characteristics of Participants Residing Within the Montreal CMA (n=512) From the Quebec Adipose and Lifestyle Investigation in Youth (QUALITY) Study Characteristic Mean (SD) age, years 9.6 (0.9) % (n) of male sex 54.5 (279) Mean (SD) annual household income, $ * 43,063 (18,722) Highest level of education of either parent, % (n) 2 parents with secondary school or less 8.3 (42) 1 or 2 parents with technical/vocational/trade 38.5 (196) degree 1 or 2 parents with university degree 53.2 (271) Mean (SD) BMI of mothers, kg/[m.sup.2] 29.5 (6.6) Mean (SD) BMI of fathers, kg/[m.sup.2] 30.8 (5.6) Mean (SD) no. of daily servings of V&F 4.3 (2.1) [greater than or equal to]5 servings of V&F per 33.7 (168) day, % (n) >50 mL of sugar-sweetened beverages per day, % (n) 58.0 (289) Eat/snack out at least once per week, % (n) 43.8 (224) Delivered/take-out food at least once per week, % (n) 35.0 (179) Residential neighbourhood Median (IQR) population density per [km.sup.2] 2715 (1926-3815) % aged [greater than or equal to]15 years with no 32.6 (9.0) high school diploma, mean (SD) % aged [greater than or equal to]15 years who are 67.0 (8.3) employed, mean (SD) Mean (SD) total income of households, $ 85,793 (23,197) Median (IQR) walking distance from residence to school, metres 1121 (631-2535) Proximity measures (distance to nearest), metres Supermarket, median (IQR) 1375 (739-2434) Fast-food restaurant, median (IQR) 1326 (784-2256) Convenience store, median (IQR) 779 (425-1327) Kernel density measures (for 1 km network buffer), no./[km.sup.2] Supermarket, median (IQR) 0.08 (0.03-0.2) Fast-food restaurant, median (IQR) 0.2 (0.08-0.8) Convenience store, median (IQR) 0.3 (0.1-1.0) Retail Food Environment Index 1 km network buffer, median (IQR) 1.0 (0-2.0) 3 km circular buffer, median (IQR) 1.8 (1.2-2.5) School neighbourhood ([dagger]) Median (IQR) population density per [km.sup.2] 2990 (2093-4087) % aged [greater than or equal to]15 years with 32.9 (9.1) no high school diploma, mean (SD) % aged [greater than or equal to]15 years who 64.0 (8.1) are employed, mean (SD) Mean (SD) total income of households, $ 81,478 (20,793) Proximity measures (distance to nearest), metres Supermarket, median (IQR) 1008 (540-1999) Fast-food restaurant, median (IQR) 950 (572-1889) Convenience store, median (IQR) 541 (311-931) Kernel density measures (for 1 km network buffer), no./[km.sup.2] Supermarket, median (IQR) 0.1 (0.03-0.3) Fast-food restaurant median (IQR) 0.3 (0.1-1.0) Convenience store median (IQR) 0.5 (0.2-1.6) Retail Food Environment Index 1 km network buffer, median (IQR) 0.8 (0-1.8) 3 km circular buffer, median (IQR) 1.7 (1.2-2.4) * Adjusted for the number of people living in the household. ([dagger]) School neighbourhood data available for 296 schools localized within the Montreal CMA attended by 506 QUALITY study children (6 attended a school outside the study area). CMA=Census Metropolitan Area; BMI=body mass index; V&F=vegetables and fruit; IQR=inter-quartile range. Table 2. Covariate-adjusted Associations (OR and 95% CI) Between Measures of the Residential Neighbourhood Food Environment and Dietary Outcomes in the QUALITY Study * [greater than or >50 mL Sugar- equal to]5 Servings sweetened of V&F/Day Beverages/Day (n=493) ([section]) (n=493) Proximity measures Model 1 - distance to nearest supermarket Farthest (>2000 m) 1.09 (0.62-1.91) 0.82 (0.48-1.39) Intermediate (965 to 2000 m) 1.07 (0.65-1.74) 0.84 (0.52-1.35) Shortest (<965 m) 1 1 Model 2 - distance to nearest fast-food restaurant Farthest (>1835 m) 1.39 (0.81-2.40) 0.82 (0.49-1.37) Intermediate (940 to 1835 m) 1.27 (0.77-2.10) 0.98 (0.61-1.58) Shortest (<940 m) 1 1 Model 3 - distance to nearest convenience store Farthest (>1090 m) 0.99 (0.57-1.72) 0.85 (0.50-1.44) Intermediate (545 to 1090 m) 0.98 (0.59-1.63) 0.87 (0.54-1.40) Shortest (<545 m) 1 1 Density measures Model 4 - density of supermarkets Lowest 1.11 (0.63-1.93) 1.20 (0.70-2.05) Intermediate 0.87 (0.52-1.48) 1.38 (0.84-2.29) Highest 1 1 Model 5 - density of fast-food restaurants Lowest 1.22 (0.68-2.22) 1.19 (0.67-2.11) Intermediate 1.01 (0.59-1.74) 1.24 (0.74-2.08) Highest 1 1 Model 6 - density of convenience stores Lowest 1.02 (0.55-1.91) 1.25 (0.69-2.27) Intermediate 1.17 (0.68-2.04) 1.19 (0.70-2.03) Highest 1 1 Retail food environment measures Model 7 - 1 km buffer RFE Index >2 (27.3%) 0.90 (0.58-1.42) 0.93 (0.61-1.43) <2 (72.7%) 1 1 Model 8 - 3 km buffer RFE Index >2.5 (26.2%) 0.77 (0.49-1.21) 0.94 (0.62-1.44) <2.5 (73.8%) 1 1 Eating/Snacking Delivered/Take- Out[greater than out Food or equal to] Once/Week Once/Week (n=506) (n=506) Proximity measures Model 1 - distance to nearest supermarket Farthest (>2000 m) 1.04 (0.62-1.73) 0.96 (0.56-1.65) Intermediate (965 to 2000 m) 1.12 (0.71-1.77) 1.47 (0.92-2.36) Shortest (<965 m) 1 1 Model 2 - distance to nearest fast-food restaurant Farthest (>1835 m) 1.03 (0.63-1.68) 1.03 (0.61-1.73) Intermediate (940 to 1835 m) 1.08 (0.69-1.71) 1.40 (0.87-2.24) Shortest (<940 m) 1 1 Model 3 - distance to nearest convenience store Farthest (>1090 m) 1.15 (0.70-1.90) 0.93 (0.55-1.56) Intermediate (545 to 1090 m) 1.23 (0.78-1.96) 1.02 (0.63-1.64) Shortest (<545 m) 1 1 Density measures Model 4 - density of supermarkets Lowest 0.63 (0.37-1.05) 0.91 (0.53-1.58) ([double dagger]) Intermediate 0.78 (0.48-1.26) 1.40 (0.85-2.29) Highest 1 1 Model 5 - density of fast-food restaurants Lowest 0.52 (0.30-0.91) 1.11 (0.63-1.98) ([dagger]) Intermediate 0.60 (0.36-0.99) 1.10 (0.66-1.84) ([dagger]) Highest 1 1 Model 6 - density of convenience stores Lowest 0.44 (0.25-0.80) 0.93 (0.51-1.70) ([dagger]) Intermediate 0.60 (0.36-1.02) 1.15 (0.68-1.95) ([double dagger]) Highest 1 1 Retail food environment measures Model 7 - 1 km buffer RFE Index >2 (27.3%) 1.01 (0.67-1.52) 1.35 (0.89-2.05) <2 (72.7%) 1 1 Model 8 - 3 km buffer RFE Index >2.5 (26.2%) 0.88 (0.59-1.33) 1.22 (0.80-1.87) <2.5 (73.8%) 1 1 * Separate logistic regression models for each main exposure and each outcome, adjusted for child's age, sex, parental education, household income, residential neighbourhood material deprivation and residential population density. ([section]) When treated as a continuous outcome, farthest (vs. shortest) distance to the nearest fast-food restaurant was associated with V&F intake (Beta=0.50, 95% CI: 0, 1.00); and 3 km RFE index 2.5 (vs. less) was associated with V&F intake (Beta=-0.40, 95% CI: -0.81, 0.005). ([dagger]) p<0.05; ([double dagger]) p<0.10. OR=odds ratio; CI=confidence interval; V&F=vegetables and fruit; RFE=retail food environment. Table 3. Covariate-adjusted Associations (OR and 95% CI) Between Measures of the School Neighbourhood Food Environment and Dietary Outcomes in the QUALITY Study * [greater than >50 mL Sugar- or equal to]5 sweetened Servings of V&F/Day Beverages/Day (n=489) ([section]) (n=489) Proximity measures Model 1 - Distance to nearest supermarket Farthest (>1565 m) 1.03 (0.63-1.68) 0.93 (0.56-1.55) Intermediate (670 to 1565 m) 1.26 (0.77-2.06) 1.00 (0.62-1.62) Shortest (<670 m) 1 1 Model 2 - Distance to nearest fast-food restaurant Farthest (>1460 m) 1.18 (0.66-2.10) 0.87 (0.51-1.48) Intermediate (680 to 1460 m) 1.59 (0.95-2.64) 0.77 (0.48-1.23) ([double dagger]) Shortest (<680 m) 1 1 Model 3 - Distance to nearest convenience store Farthest (>834 m) 1.13 (0.66-1.91) 0.99 (0.58-1.68) Intermediate (370 to 835 m) 1.10 (0.68-1.81) 1.48 (0.91-2.39) Shortest (<370 m) 1 1 Density measures Model 4 - Density of supermarkets Lowest 0.99 (0.55-1.78) 1.37 (0.74-2.51) Intermediate 0.82 (0.49-1.35) 1.64 (0.96-2.79) ([double dagger]) Highest 1 1 Model 5 - Density of fast-food restaurants Lowest 1.59 (0.85-2.94) 0.97 (0.54-1.75) Intermediate 1.25 (0.69-2.25) 1.06 (0.64-1.76) Highest 1 1 Model 6 - Density of convenience stores Lowest 1.34 (0.69-2.60) 1.04 (0.56-1.93) Intermediate 1.39 (0.80-2.41) 0.98 (0.59-1.61) Highest 1 1 Retail food environment measures Model 7 - 1 km buffer RFE Index 2 (21.9%) 0.63 (0.39-1.04) 0.96 (0.60-1.51) ([double dagger]) <2 (78.1%) 1 1 Model 8 - 3 km buffer RFE Index 2.5 (22.9%) 0.67 (0.41-1.08) 1.61 (1.01-2.56) ([double dagger]) ([dagger]) <2.5 (77.1%) 1 1 Eating/Snacking Delivered/Take- Out [greater than out Food [greater or equal to] than or equal to] Once/Week Once/Week (n=502) (n=502) Proximity measures Model 1 - Distance to nearest supermarket Farthest (>1565 m) 1.05 (0.67-1.65) 1.14 (0.70-1.86) Intermediate (670 to 1565 m) 1.20 (0.79-1.81) 1.14 (0.73-1.78) Shortest (<670 m) 1 1 Model 2 - Distance to nearest fast-food restaurant Farthest (>1460 m) 1.23 (0.79-1.94) 1.34 (0.84-2.14) Intermediate (680 to 1460 m) 1.39 (0.89-2.17) 1.22 (0.77-1.93) Shortest (<680 m) 1 1 Model 3 - Distance to nearest convenience store Farthest (>834 m) 1.10 (0.69-1.77) 1.08 (0.68-1.71) Intermediate (370 to 835 m) 0.94 (0.61-1.47) 0.69 (0.43-1.10) Shortest (<370 m) 1 1 Density measures Model 4 - Density of supermarkets Lowest 0.63 (0.37-1.06) 0.97 (0.56-1.67) ([double dagger]) Intermediate 0.78 (0.48-1.28) 1.55 (0.91-2.64) Highest 1 1 Model 5 - Density of fast-food restaurants Lowest 0.85 (0.50-1.47) 1.25 (0.71-2.20) Intermediate 0.96 (0.58-1.57) 1.53 (0.93-2.50) ([double dagger]) Highest 1 1 Model 6 - Density of convenience stores Lowest 0.71 (0.38-1.35) 0.75 (0.41-1.35) Intermediate 0.81 (0.47-1.41) 1.03 (0.61-1.73) Highest 1 1 Retail food environment measures Model 7 - 1 km buffer RFE Index 2 (21.9%) 0.74 (0.47-1.15) 0.93 (0.61-1.41) <2 (78.1%) 1 1 Model 8 - 3 km buffer RFE Index 2.5 (22.9%) 0.83 (0.53-1.30) 1.25 (0.81-1.91) <2.5 (77.1%) 1 1 * Separate GEE (generalized estimating equations) model with logit link function for each main exposure and each outcome, adjusted for child's age, sex, parental education, household income, school neighbourhood material deprivation and school neighbourhood population density. ([dagger]) p<0.05; ([double dagger]) p<0.10. ([section]) When treated as a continuous outcome, 3 km RFE Index 2.5 (vs. less) was associated with V&F intake (Beta= -0.50, 95% CI: -0.91, -0.09). OR=odds ratio; CI=confidence interval; V&F=vegetables and fruit; RFE=retail food environment. Table 4. Covariate-adjusted Associations (OR and 95% CI) of Residential and School Neighbourhood Densities of Food Establishments with Dietary Outcomes in Children Living More Than 1.5 km From Their School, QUALITY Study >50 mL Sugar- [greater than or equal to]5 sweetened Servings of V&F/Day Beverages/Day (n=189) (n=189) Residential environment * Model 1 - Density of supermarkets Lowest 1.01 (0.38-2.69) 1.00 (0.38-2.63) Intermediate 0.79 (0.33-1.88) 1.32 (0.56-3.12) Highest 1 1 Model 2 - Density of fast-food restaurants Lowest 0.91 (0.32-2.53) 1.69 (0.62-4.64) Intermediate 0.67 (0.27-1.65) 1.22 (0.51-2.95) Highest 1 1 Model 3 - Density of convenience stores Lowest 0.71 (0.24-2.08) 1.53 (0.53-4.40) Intermediate 0.56 (0.21-1.45) 1.45 (0.57-3.69) Highest 1 1 School environment ** Model 4 - Density of supermarkets 1.70 (0.63-4.60) 0.72 (0.28-1.88) Intermediate 1.06 (0.49-2.30 1.01 (0.45-2.26) Highest 1 1 Model 5 - Density of fast-food restaurants Lowest 2.87 (1.16-7.10) ([dagger]) 1.04 (0.46-2.37) Intermediate 0.87 (0.34-2.21) 1.31 (0.54-3.19) Highest 1 1 Model 6 - Density of convenience stores Lowest 2.21 (0.76-6.47) 0.58 (0.20-1.68) Intermediate 0.93 (0.37-2.37) 0.70 (0.25-1.92) Highest 1 1 Eating/Snacking Out [greater Delivered/Take-out Food than or equal to] [greater than or equal to] Once/Week Once/Week (n=191) (n=191) Residential environment * Model 1 - Density of supermarkets Lowest 0.66 (0.25-1.72) 1.27 (0.44-3.66) Intermediate 0.70 (0.30-1.63) 2.13 (0.86-5.31) ([double dagger]) Highest 1 1 Model 2 - Density of fast-food restaurants Lowest 0.67 (0.25-1.79) 3.45 (1.10-10.84) ([dagger]) Intermediate 0.79 (0.34-1.87) 1.81 (0.70-4.73) Highest 1 1 Model 3 - Density of convenience stores Lowest 0.32 (0.11-0.93)! 1.78 (0.57-5.60) Intermediate 0.41 (0.16-1.05)1 1.67 (0.62-4.51) Highest 1 1 School environment ** Model 4 - Density of supermarkets 0.76 (0.31-1.90) 0.80 (0.26-2.48) Intermediate 1.17 (0.54-2.53) 1.49 (0.60-3.71) Highest 1 1 Model 5 - Density of fast-food restaurants Lowest 1.63 (0.70-3.82) 1.51 (0.58-3.93) Intermediate 1.76 (0.83-3.72) 2.84 (1.16-6.97) ([dagger]) Highest 1 1 Model 6 - Density of convenience stores Lowest 1.26 (0.47-3.35) 0.53 (0.16-1.81) Intermediate 1.19 (0.53-2.69) 0.98 (0.32-3.04) Highest 1 1 Eating/Snacking Out [greater Delivered/Take-out Food than or equal to] [greater than or equal to] Once/Week Once/Week (n=191) (n=191) * Separate logistic regression models for each exposure and each outcome, adjusted for child's age, sex, parental education, household income, residential neighbourhood material deprivation and residential population density. ** Separate GEE (generalized estimating equations) models with logit link function for each exposure and each outcome, adjusted for child's age, sex, parental education, household income, school neighbourhood material deprivation and school neighbourhood population density. ([dagger]) p<0.05, ([double dagger]) p<0.10. OR=odds ratio; CI=confidence interval; V&F=vegetables and fruit.