You are here

  • Home
  • Archive
  • Volume 72, Issue 3
  • Neighbourhood looking glass: 360º automated characterisation of the built environment for neighbourhood effects research

Article Text

Article menu

Download PDFPDF

Research report
Neighbourhood looking glass: 360º automated characterisation of the built environment for neighbourhood effects research
  1. Quynh C Nguyen1,
  2. Mehdi Sajjadi2,
  3. Matt McCullough3,
  4. Minh Pham4,
  5. Thu T Nguyen5,
  6. Weijun Yu6,
  7. Hsien-Wen Meng6,
  8. Ming Wen7,
  9. Feifei Li4,
  10. Ken R Smith8,
  11. Kim Brunisholz9,
  12. Tolga Tasdizen2
  1. 1 Department of Epidemiology and Biostatistics, University of Maryland School of Public Health, College Park, Maryland, USA
  2. 2 Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, Utah, USA
  3. 3 Department of Geography, University of Utah, Salt Lake City, Utah, USA
  4. 4 School of Computing, University of Utah, Salt Lake City, Utah, USA
  5. 5 Department of Epidemiology and Biostatistics, University of California San Francisco School of Medicine, San Francisco, California, USA
  6. 6 Department of Health, Kinesiology, and Recreation, University of Utah, Salt Lake City, Utah, United States
  7. 7 Department of Sociology, University of Utah, Salt Lake City, Utah, USA
  8. 8 Department of Family and Consumer Studies and Population Sciences, Huntsman Cancer Institute, University of Utah, Salt Lake City, Utah, USA
  9. 9 Institute for Healthcare Delivery Research, Intermountain Healthcare, Salt Lake City, Utah, USA
  1. 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{at}gmail.com

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.

  • neighborhood/place
  • obesity
  • diabetes
  • gis
  • methodology

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/

https://doi.org/10.1136/jech-2017-209456

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    View Full Text

    Footnotes

    • Contributors QCN took the lead in designing the study, implementing analyses and writing the manuscript. MS and TT devised and implemented computer vision approaches to process the Google Street View images. MM and MP obtained Google Street View images via the Google Street View API, mapped the data and edited the manuscript. TXN, WY, H-WM, MW, FL, KRS and KB assisted with the design of the study and edited the manuscript.

    • Funding This work was supported by NIH grants 5K01ES025433 and 3K01ES025433-03S1 (Dr Nguyen, PI).

    • Competing interests None declared.

    • Patient consent Our study involved analyses of de-identified records.

    • Ethics approval The University of Utah Institutional Review Board approved the study.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Data sharing statement Zip code and census tract level indicators of the built environment indicators developed for this manuscript can be downloaded at our project website: https://hashtaghealth.github.io/geoportal/start.html