8
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Neighbourhood looking glass: 360º automated characterisation of the built environment for neighbourhood effects research

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background

          Neighbourhood quality has been connected with an array of health issues, but neighbourhood research has been limited by the lack of methods to characterise large geographical areas. This study uses innovative computer vision methods and a new big data source of street view images to automatically characterise neighbourhood built environments.

          Methods

          A total of 430 000 images were obtained using Google’s Street View Image API for Salt Lake City, Chicago and Charleston. Convolutional neural networks were used to create indicators of street greenness, crosswalks and building type. We implemented log Poisson regression models to estimate associations between built environment features and individual prevalence of obesity and diabetes in Salt Lake City, controlling for individual-level and zip code-level predisposing characteristics.

          Results

          Computer vision models had an accuracy of 86%–93% compared with manual annotations. Charleston had the highest percentage of green streets (79%), while Chicago had the highest percentage of crosswalks (23%) and commercial buildings/apartments (59%). Built environment characteristics were categorised into tertiles, with the highest tertile serving as the referent group. Individuals living in zip codes with the most green streets, crosswalks and commercial buildings/apartments had relative obesity prevalences that were 25%–28% lower and relative diabetes prevalences that were 12%–18% lower than individuals living in zip codes with the least abundance of these neighbourhood features.

          Conclusion

          Neighbourhood conditions may influence chronic disease outcomes. Google Street View images represent an underused data resource for the construction of built environment features.

          Related collections

          Most cited references34

          • Record: found
          • Abstract: not found
          • Article: not found

          Environmental factors associated with adults' participation in physical activity: a review.

          N Humpel (2002)
          Promoting physical activity is a public health priority, and changes in the environmental contexts of adults' activity choices are believed to be crucial. However, of the factors associated with physical activity, environmental influences are among the least understood. Using journal scans and computerized literature database searches, we identified 19 quantitative studies that assessed the relationships with physical activity behavior of perceived and objectively determined physical environment attributes. Findings were categorized into those examining five categories: accessibility of facilities, opportunities for activity, weather, safety, and aesthetic attributes. Accessibility, opportunities, and aesthetic attributes had significant associations with physical activity. Weather and safety showed less-strong relationships. Where studies pooled different categories to create composite variables, the associations were less likely to be statistically significant. Physical environment factors have consistent associations with physical activity behavior. Further development of ecologic and environmental models, together with behavior-specific and context-specific measurement strategies, should help in further understanding of these associations. Prospective studies are required to identify possible causal relationships.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Bringing context back into epidemiology: variables and fallacies in multilevel analysis.

            A large portion of current epidemiologic research is based on methodologic individualism: the notion that the distribution of health and disease in populations can be explained exclusively in terms of the characteristics of individuals. The present paper discusses the need to include group- or macro-level variables in epidemiologic studies, thus incorporating multiple levels of determination in the study of health outcomes. These types of analyses, which have been called contextual or multi-level analyses, challenge epidemiologists to develop theoretical models of disease causation that extend across levels and explain how group-level and individual-level variables interact in shaping health and disease. They also raise a series of methodological issues, including the need to select the appropriate contextual unit and contextual variables, to correctly specify the individual-level model, and, in some cases, to account for residual correlation between individuals within contexts. Despite its complexities, multilevel analysis holds potential for reemphasizing the role of macro-level variables in shaping health and disease in populations.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Birth weight and subsequent risk of obesity: a systematic review and meta-analysis.

              This report describes the association between birth weight (BW) and obesity. Screening of 478 citations from five electronic databases resulted in the inclusion of 33 studies, most of medium quality. The meta-analysis included 20 of these published studies. The 13 remaining articles did not provide sufficient dichotomous data and were systematically reviewed, revealing results consistent with the meta-analysis. Our results revealed that high BW (>4000 g) was associated with increased risk of obesity (odds ratio [OR], 2.07; 95% confidence interval [CI], 1.91-2.24) compared with subjects with BW ≤ 4000 g. Low BW (<2500 g) was associated with decreased risk of obesity (OR, 0.61; 95% CI, 0.46-0.80) compared with subjects with BW ≥ 2500 g. However, when two studies exhibited selection bias were removed, the results indicated no significant association between low BW and obesity (OR, 0.77; 95% CI, 0.58-1.04). Sensitivity analyses showed that differences in the study design, sample size and quality grade of the study had an effect on the low BW/obesity association, which low BW was not associated with the risk of obesity in cohort studies, studies with large sample sizes and studies with high quality grades. Pooled results were similar when normal birth weight (2500-4000 g) was used as the reference category. Subgroup analyses based on different growth and developmental stages (pre-school children, school children and adolescents) also revealed that high BW was associated with increased risk of obesity from childhood to early adulthood. No significant evidence of publication bias was present. These results suggest that high BW is associated with increased risk of obesity and may serve as a mediator between prenatal influences and later disease risk. © 2011 The Authors. obesity reviews © 2011 International Association for the Study of Obesity.
                Bookmark

                Author and article information

                Journal
                J Epidemiol Community Health
                J Epidemiol Community Health
                jech
                jech
                Journal of Epidemiology and Community Health
                BMJ Publishing Group (BMA House, Tavistock Square, London, WC1H 9JR )
                0143-005X
                1470-2738
                March 2018
                15 January 2018
                : 72
                : 3
                : 260-266
                Affiliations
                [1 ] departmentDepartment of Epidemiology and Biostatistics , University of Maryland School of Public Health , College Park, Maryland, USA
                [2 ] departmentDepartment of Electrical and Computer Engineering , University of Utah , Salt Lake City, Utah, USA
                [3 ] departmentDepartment of Geography , University of Utah , Salt Lake City, Utah, USA
                [4 ] departmentSchool of Computing , University of Utah , Salt Lake City, Utah, USA
                [5 ] departmentDepartment of Epidemiology and Biostatistics , University of California San Francisco School of Medicine , San Francisco, California, USA
                [6 ] departmentDepartment of Health, Kinesiology, and Recreation , University of Utah , Salt Lake City, Utah, United States
                [7 ] departmentDepartment of Sociology , University of Utah , Salt Lake City, Utah, USA
                [8 ] departmentDepartment of Family and Consumer Studies and Population Sciences, Huntsman Cancer Institute , University of Utah , Salt Lake City, Utah, USA
                [9 ] departmentInstitute for Healthcare Delivery Research , Intermountain Healthcare , Salt Lake City, Utah, USA
                Author notes
                [Correspondence to ] Dr Quynh C Nguyen, Department of Epidemiology and Biostatistics, University of Maryland School of Public Health, College Park, MD 20742, USA; quynh.ctn@ 123456gmail.com
                Author information
                http://orcid.org/0000-0003-4745-6681
                Article
                jech-2017-209456
                10.1136/jech-2017-209456
                5868527
                29335255
                9da5d3ff-bad0-4971-bc01-230b6c8cdbd8
                © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

                This is an Open Access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/

                History
                : 12 May 2017
                : 02 October 2017
                : 18 December 2017
                Funding
                Funded by: FundRef http://dx.doi.org/10.13039/100000066, National Institute of Environmental Health Sciences;
                Categories
                Research Report
                1506
                Custom metadata
                unlocked

                Public health
                neighborhood/place,obesity,diabetes,gis,methodology
                Public health
                neighborhood/place, obesity, diabetes, gis, methodology

                Comments

                Comment on this article