A model-based approach to select case sites for walkability audits

Integrating street view images and deep learning to explore the association between human perceptions of the built environment and cardiovascular disease in older adults

Understanding how built environment attributes affect health remains important. While many studies have explored the objective characteristics of built environments that affect health outcomes, few have examined the role of human perceptions of built environments on physical health. Baidu Street View images and computer vision technological advances have helped researchers overcome the constraints of traditional methods of measuring human perceptions (e.g., these methods are laborious, time-consuming, and costly), allowing for large-scale measurements of human perceptions. This study estimated human perceptions of the built environment (e.g., beauty, boredom, depression, safety, vitality, and wealth) by adopting Baidu Street View images and deep learning algorithms. Negative binomial regression models were employed to analyze the relationship between human perceptions and cardiovascular disease in older adults (e.g., ischemic heart disease and cerebrovascular disease). The results indicated that wealth perception is negatively related to the risk of cardiovascular disease. However, depression and vitality perceptions are positively associated with the risk of cardiovascular disease. Furthermore, we found no relationship between beauty, boredom, safety perceptions, and the risk of cardiovascular disease. Our findings highlight the importance of human perceptions in the development of healthy city planning and facilitate a comprehensive understanding of the relationship between built environment characteristics and health outcomes in older adults. They also demonstrate that street view images have the potential to provide insights into this complicated issue, assisting in the formulation of refined interventions and health policies.

Spatial scale analysis for the relationships between the built environment and cardiovascular disease based on multi-source data

To examine what built environment characteristics improve the health outcomes of human beings is always a hot issue. While a growing literature has analyzed the link between the built environment and health, few studies have investigated this relationship across different spatial scales. In this study, eighteen variables were selected from multi-source data and reduced to eight built environment attributes using principal component analysis. These attributes included socioeconomic deprivation, urban density, street walkability, land-use diversity, blue-green space, transportation convenience, ageing, and street insecurity. Multiscale geographically weighted regression was then employed to clarify how these attributes relate to cardiovascular disease at different scales. The results indicated that: (1) multiscale geographically weighted regression showed a better fit of the association between the built environment and cardiovascular diseases than other models (e.g., ordinary least squares and geographically weighted regression), and is thus an effective approach for multiscale analysis of the built environment and health associations; (2) built environment variables related to cardiovascular diseases can be divided into global variables with large scales (e.g., socioeconomic deprivation, street walkability, land-use diversity, blue-green space, transportation convenience, and ageing) and local variables with small scales (e.g., urban density and street insecurity); and (3) at specific spatial scales, global variables had trivial spatial variation across the area, while local variables showed significant gradients. These findings provide greater insight into the association between the built environment and lifestyle-related diseases in densely populated cities, emphasizing the significance of hierarchical and place-specific policy formation in health interventions.

The influence of neighborhood quality on tourism in China: Using Baidu Street View pictures and deep learning techniques

Previous studies have investigated the determinants of urban tourism development from the various attributes of neighborhood quality. However, traditional methods to assess neighborhood quality are often subjective, costly, and only on a small scale. To fill this research gap, this study applies the recent development in big data of street view images, deep learning algorithms, and image processing technology to assess quantitatively four attributes of neighborhood quality, namely street facilities, architectural landscape, green or ecological environment, and scene visibility. The paper collects more than 7.8 million Baidu SVPs of 232 prefecture-level cities in China and applies deep learning techniques to recognize these images. This paper then tries to examine the influence of neighborhood quality on regional tourism development. Empirical results show that both levels of street facilities and greenery environment promote tourism. However, the construction intensity of the landscape has an inhibitory influence on the development of tourism. The threshold test shows that the intensity of the influence varies with the city's overall economic level. These conclusions are of great significance for the development of China's urban construction and tourism economy, and also provide a useful reference for policymakers. The methodological procedure is reduplicative and can be applied to other challenging cases.

Social Infrastructure and Street Networks as Critical Infrastructure for Aging Friendly Community Design: Mediating the Effect of Physical Activity

Establishing an age-friendly environment at the community level is essential for promoting healthy aging. This study focused on the relationship between older adults and the community environment through their levels of satisfaction within it. We measured their physical activity (PA) in the community environment and three variables of community-level satisfaction: community environment (SCE), community social infrastructure (SSI), and community street networks (SSN). We analyzed 108 older adult participants in Suzhou using mediation analysis and multiple linear regression to investigate the relationship between physical activity and the community environment. The results of the mediation effect model showed that SCE, SSI, and SSN all affected the physical functions of older adults via the total amount of physical activity (TPA); SSI and SSN affected older adults' physical functions by affecting the total duration of moderate-intensity physical activity (MPA) and vigorous-intensity physical activity (VPA). In addition, SSI and SSN are related to the types of community facilities, street space quality, and accessibility. Our study provides valuable insights into optimizing aging-friendly neighborhoods through moderate-to-vigorous-intensity PAs at both the facility and street space levels.

A dual-method approach toward measuring the built environment - sampling optimization, validity, and efficiency of using GIS and virtual auditing

In recent years, GIS and virtual auditing have been widely used to measure the built environment, and each method carries its strengths and weaknesses. To generate higher quality, more cost-effective, and less time-consuming measures, it is necessary to explore dual- or multi-method strategy toward sampling optimization, improvement of measurement, and enhancement of efficiency. To justify the proposed dual-method approach, the study has three major objectives. First, it examines the uncertainties associated with different sample sizes by using GIS to generate scenarios that contrast the validity of measurements to aid sampling optimization in auditing. Second, it compares the validity of GIS measures with those generated through Google Street View Auditing (GSVA) by human raters. Third, it further examines the efficiency of the proposed dual-method approach in comparison to the two individual methods. Such investigation generates several novel findings. First, the study presents important evidence to support that GIS measures can offer sampling guidance applicable to the GSVA method. It leads to a recommendation of sampling sizes (5%-20%) for cases in settings with a mixture of affluent and disadvantaged neighborhoods. Results further indicate that different communities and certain individual features and characteristics may demand different sampling practices. Second, the study found that while GSVA is trustworthy for most characteristic variables, especially those that required subjective input, GIS provides well-validated measures for certain objective environmental attributes. Furthermore, the study reports that a dual-method approach of GIS and GSVA had a lower financial and time burden than using GSVA alone and is thus recommended as a comprehensive solution for optimal measurement of an objective built environment in mixed urban neighborhoods.

Sampling Methodology and Reliability of a Representative Walkability Audit

Background

Physical inactivity is a public health concern in the US Virgin Islands (USVI). A contributing factor may be a lack of pedestrian infrastructure and other environmental supports for walking. In this manuscript, we describe the methods used to conduct a walkability audit of environmental features related to physical activity in the USVI.

Methods

In 2016, volunteer auditors conducted the audit using a modified version of the Microscale Audit of Pedestrian Streetscapes tool. A two-stage sampling method was developed using publicly available census data to select a sample of estates (n=46) and street segments (n=1,550; 99.2 km) across the USVI. A subset of segments was audited by two independent auditors, and inter-rater reliability was assessed using Cohen's kappa and percent agreement.

Results

Audits were completed on 1,114 segments (94.6 km), and estimates were weighted to represent accessible public street length in the study area (1,155.9 km). Most items on the audit tool (62.7%) demonstrated good to excellent reliability. We found that it was feasible to conduct a reliable audit of environmental features related to physical activity across a large sample of streets in the USVI.

Conclusions

These methods can be replicated in other settings to collect comprehensive data that can be used to guide strategies to improve the walkability of communities.

One size doesn't fit all: cross-sectional associations between neighborhood walkability, crime and physical activity depends on age and sex of residents

BACKGROUND

Low-income African American adults are disproportionately affected by obesity and are also least likely to engage in recommended levels of physical activity (Flegal et al. JAMA 303(3):235-41, 2010; Tucker et al. Am J Prev Med 40(4):454-61, 2011). Moderate-to-vigorous physical activity (MVPA) is an important factor for weight management and control, as well as for reducing disease risk (Andersen et al. Lancet 368(9532):299-304, 2006; Boreham and Riddoch J Sports Sci 19(12):915-29, 2001; Carson et al. PLoS One 8(8):e71417, 2013). While neighborhood greenspace and walkability have been associated with increased MVPA, evidence also suggests that living in areas with high rates of crime limits MVPA. Few studies have examined to what extent the confluence of neighborhood greenspace, walkability and crime might impact MVPA in low-income African American adults nor how associations may vary by age and sex.

METHODS

In 2013 we collected self-reported data on demographics, functional limitations, objective measures of MVPA (accelerometry), neighborhood greenspace (geographic information system), and walkability (street audit) in 791 predominantly African-American adults (mean age 56 years) living in two United States (U.S.) low-income neighborhoods. We also acquired data from the City of Pittsburgh on all crime events within both neighborhoods.

EXPOSURE

To examine cross-sectional associations of neighborhood-related variables (i.e., neighborhood greenspace, walkability and crime) with MVPA, we used zero-inflated negative binomial regression models. Additionally, we examined potential interactions by age (over 65 years) and sex on relationships between neighborhood variables and MVPA.

RESULTS

Overall, residents engaged in very little to no MVPA regardless of where they lived. However, for women, but not men, under the age of 65 years, living in more walkable neighborhoods was associated with more time engaged in MVPA in (β = 0.55, p = 0.007) as compared to their counterparts living in less walkable areas. Women and men age 65 years and over spent very little time participating in MVPA regardless of neighborhood walkability. Neither greenspace nor crime was associated with MVPA in age-sex subgroups.

CONCLUSIONS

Neighborhood walkability may play a stronger role on MVPA than accessible greenspace or crime in low-income urban communities. Walkability may differentially impact residents depending on their age and sex, which suggests tailoring public health policy design and implementation according to neighborhood demographics to improve activity for all.