Cargando…

Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes

Built environment neighborhood characteristics are difficult to measure and assess on a large scale. Consequently, there is a lack of sufficient data that can help us investigate neighborhood characteristics as structural determinants of health on a national level. The objective of this study is to...

Descripción completa

Detalles Bibliográficos
Autores principales: Yue, Xiaohe, Antonietti, Anne, Alirezaei, Mitra, Tasdizen, Tolga, Li, Dapeng, Nguyen, Leah, Mane, Heran, Sun, Abby, Hu, Ming, Whitaker, Ross T., Nguyen, Quynh C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9564970/
https://www.ncbi.nlm.nih.gov/pubmed/36231394
http://dx.doi.org/10.3390/ijerph191912095
_version_ 1784808777156919296
author Yue, Xiaohe
Antonietti, Anne
Alirezaei, Mitra
Tasdizen, Tolga
Li, Dapeng
Nguyen, Leah
Mane, Heran
Sun, Abby
Hu, Ming
Whitaker, Ross T.
Nguyen, Quynh C.
author_facet Yue, Xiaohe
Antonietti, Anne
Alirezaei, Mitra
Tasdizen, Tolga
Li, Dapeng
Nguyen, Leah
Mane, Heran
Sun, Abby
Hu, Ming
Whitaker, Ross T.
Nguyen, Quynh C.
author_sort Yue, Xiaohe
collection PubMed
description Built environment neighborhood characteristics are difficult to measure and assess on a large scale. Consequently, there is a lack of sufficient data that can help us investigate neighborhood characteristics as structural determinants of health on a national level. The objective of this study is to utilize publicly available Google Street View images as a data source for characterizing built environments and to examine the influence of built environments on chronic diseases and health behaviors in the United States. Data were collected by processing 164 million Google Street View images from November 2019 across the United States. Convolutional Neural Networks, a class of multi-layer deep neural networks, were used to extract features of the built environment. Validation analyses found accuracies of 82% or higher across neighborhood characteristics. In regression analyses controlling for census tract sociodemographics, we find that single-lane roads (an indicator of lower urban development) were linked with chronic conditions and worse mental health. Walkability and urbanicity indicators such as crosswalks, sidewalks, and two or more cars were associated with better health, including reduction in depression, obesity, high blood pressure, and high cholesterol. Street signs and streetlights were also found to be associated with decreased chronic conditions. Chain link fence (physical disorder indicator) was generally associated with poorer mental health. Living in neighborhoods with a built environment that supports social interaction and physical activity can lead to positive health outcomes. Computer vision models using manually annotated Google Street View images as a training dataset were able to accurately identify neighborhood built environment characteristics. These methods increases the feasibility, scale, and efficiency of neighborhood studies on health.
format Online
Article
Text
id pubmed-9564970
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-95649702022-10-15 Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes Yue, Xiaohe Antonietti, Anne Alirezaei, Mitra Tasdizen, Tolga Li, Dapeng Nguyen, Leah Mane, Heran Sun, Abby Hu, Ming Whitaker, Ross T. Nguyen, Quynh C. Int J Environ Res Public Health Article Built environment neighborhood characteristics are difficult to measure and assess on a large scale. Consequently, there is a lack of sufficient data that can help us investigate neighborhood characteristics as structural determinants of health on a national level. The objective of this study is to utilize publicly available Google Street View images as a data source for characterizing built environments and to examine the influence of built environments on chronic diseases and health behaviors in the United States. Data were collected by processing 164 million Google Street View images from November 2019 across the United States. Convolutional Neural Networks, a class of multi-layer deep neural networks, were used to extract features of the built environment. Validation analyses found accuracies of 82% or higher across neighborhood characteristics. In regression analyses controlling for census tract sociodemographics, we find that single-lane roads (an indicator of lower urban development) were linked with chronic conditions and worse mental health. Walkability and urbanicity indicators such as crosswalks, sidewalks, and two or more cars were associated with better health, including reduction in depression, obesity, high blood pressure, and high cholesterol. Street signs and streetlights were also found to be associated with decreased chronic conditions. Chain link fence (physical disorder indicator) was generally associated with poorer mental health. Living in neighborhoods with a built environment that supports social interaction and physical activity can lead to positive health outcomes. Computer vision models using manually annotated Google Street View images as a training dataset were able to accurately identify neighborhood built environment characteristics. These methods increases the feasibility, scale, and efficiency of neighborhood studies on health. MDPI 2022-09-24 /pmc/articles/PMC9564970/ /pubmed/36231394 http://dx.doi.org/10.3390/ijerph191912095 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yue, Xiaohe
Antonietti, Anne
Alirezaei, Mitra
Tasdizen, Tolga
Li, Dapeng
Nguyen, Leah
Mane, Heran
Sun, Abby
Hu, Ming
Whitaker, Ross T.
Nguyen, Quynh C.
Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title_full Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title_fullStr Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title_full_unstemmed Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title_short Using Convolutional Neural Networks to Derive Neighborhood Built Environments from Google Street View Images and Examine Their Associations with Health Outcomes
title_sort using convolutional neural networks to derive neighborhood built environments from google street view images and examine their associations with health outcomes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9564970/
https://www.ncbi.nlm.nih.gov/pubmed/36231394
http://dx.doi.org/10.3390/ijerph191912095
work_keys_str_mv AT yuexiaohe usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT antoniettianne usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT alirezaeimitra usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT tasdizentolga usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT lidapeng usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT nguyenleah usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT maneheran usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT sunabby usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT huming usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT whitakerrosst usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes
AT nguyenquynhc usingconvolutionalneuralnetworkstoderiveneighborhoodbuiltenvironmentsfromgooglestreetviewimagesandexaminetheirassociationswithhealthoutcomes