Harrington Heart and Vascular Institute, University Hospitals, 11100 Euclid Ave, Cleveland, OH 44106, USA.
School of Medicine, Case Western Reserve University, 10900 Euclid Ave, Cleveland, OH 44106, USA.
Eur Heart J. 2024 May 7;45(17):1540-1549. doi: 10.1093/eurheartj/ehae158.
Built environment plays an important role in the development of cardiovascular disease. Tools to evaluate the built environment using machine vision and informatic approaches have been limited. This study aimed to investigate the association between machine vision-based built environment and prevalence of cardiometabolic disease in US cities.
This cross-sectional study used features extracted from Google Street View (GSV) images to measure the built environment and link them with prevalence of coronary heart disease (CHD). Convolutional neural networks, linear mixed-effects models, and activation maps were utilized to predict health outcomes and identify feature associations with CHD at the census tract level. The study obtained 0.53 million GSV images covering 789 census tracts in seven US cities (Cleveland, OH; Fremont, CA; Kansas City, MO; Detroit, MI; Bellevue, WA; Brownsville, TX; and Denver, CO).
Built environment features extracted from GSV using deep learning predicted 63% of the census tract variation in CHD prevalence. The addition of GSV features improved a model that only included census tract-level age, sex, race, income, and education or composite indices of social determinant of health. Activation maps from the features revealed a set of neighbourhood features represented by buildings and roads associated with CHD prevalence.
In this cross-sectional study, the prevalence of CHD was associated with built environment factors derived from GSV through deep learning analysis, independent of census tract demographics. Machine vision-enabled assessment of the built environment could potentially offer a more precise approach to identify at-risk neighbourhoods, thereby providing an efficient avenue to address and reduce cardiovascular health disparities in urban environments.
建筑环境对心血管疾病的发展起着重要作用。使用机器视觉和信息学方法评估建筑环境的工具一直受到限制。本研究旨在调查基于机器视觉的建筑环境与美国城市中心血管代谢疾病患病率之间的关联。
本横断面研究使用从谷歌街景（GSV）图像中提取的特征来衡量建筑环境，并将其与冠心病（CHD）的患病率联系起来。利用卷积神经网络、线性混合效应模型和激活图来预测健康结果，并在普查区层面识别与 CHD 相关的特征关联。该研究在美国七个城市（俄亥俄州克利夫兰、加利福尼亚州弗里蒙特、密苏里州堪萨斯城、密歇根州底特律、华盛顿州贝尔维尤、德克萨斯州布朗斯维尔和科罗拉多州丹佛）获得了涵盖 789 个普查区的 53 万张 GSV 图像。
使用深度学习从 GSV 中提取的建筑环境特征预测了 CHD 患病率在普查区层面的 63%变异。在仅包含普查区层面年龄、性别、种族、收入和教育或社会决定因素综合指数的模型中添加 GSV 特征后，该模型得到了改善。来自特征的激活图揭示了一组由建筑物和道路代表的与 CHD 患病率相关的邻里特征。
在这项横断面研究中，CHD 的患病率与通过深度学习分析从 GSV 获得的建筑环境因素相关，独立于普查区人口统计学特征。机器视觉支持的建筑环境评估有可能提供一种更精确的方法来识别高风险社区，从而为解决和减少城市环境中的心血管健康差异提供一条有效途径。
