Alcohol outlets and firearm violence: a place-based case-control study using satellite imagery and machine learning.
Alcohol outlets and firearm violence: a place-based case-control study using satellite imagery and machine learning.
复制标题
DOI：
10.1136/injuryprev-2019-043248
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Jay J
中科院分区：
文献类型：
--
作者：
Jay J
本文提出了一种基于视觉相似性的匹配地点的新方法，使用高分辨率卫星图像和机器学习。当建筑环境是一个潜在的混杂因素时，如在许多伤害研究中，这种方法加强了比较。作为一个例子，我运用这种方法研究了在宾夕法尼亚州费城，特别是啤酒商店和酒吧/餐馆的酒精销售点（AOs）对枪支暴力的空间影响。使用病例对照框架，基于预训练卷积神经网络和t分布随机邻居嵌入的分析，将2017-2018年发生枪击事件的城市街区与没有枪击事件的相似街区进行匹配。使用逻辑回归来估计与AO在同一街区以及在一个街区和两个街区距离内的枪击事件的OR，条件是附加因素，如土地使用，人口构成和非法毒品活动。病例-对照匹配在视觉外观、人工检查上相似，并且在协变量测量上很好地平衡。完全调整后的模型估计，一个街区内有啤酒店的地点枪击风险增加，OR=1.5, 95% CI 1.1至2.1,p=0.02，而同一街区有酒吧/餐馆的地点，OR=1.6, 95% CI 1.1至2.4,p=0.02。这些发现与之前的研究结果一致，同时解决了aoo可能系统地位于某些环境中的担忧，为附近枪支暴力的因果关系提供了更有力的证据。视觉相似性的匹配可以改善基于地点风险的观察性损伤研究。
This article proposes a novel method for matching places based on visual similarity, using high-resolution satellite imagery and machine learning. This approach strengthens comparisons when the built environment is a potential confounder, as in many injury research studies. As an example, I apply this method to study the spatial influence of alcohol outlets (AOs)on firearm violence in Philadelphia, Pennsylvania, specifically beer stores and bar/restaurants. Using a case–control framework, city blocks with shootings in 2017–2018 were matched with similar-looking blocks with no shootings, based on analysis with a pretrained convolutional neural network and t-distributed stochastic neighbour embedding. Logistic regression was used to estimate the OR of a shooting on the same block as an AO and within one-block and two-block distances, conditional on additional factors such as land use, demographic composition and illegal drug activity. The case–control matches were similar in visual appearance, on human inspection, and were well balanced on covariate measures. The fully adjusted model estimated an increased shootings risk for locations with beer stores within one block, OR=1.5, 95% CI 1.1 to 2.1, p=0.02, and locations with bar/restaurants on the same block, OR=1.6, 95% CI 1.1 to 2.4, p=0.02. These findings align with previous study findings while addressing the concern that AOs might systematically be located in certain kinds of environments, providing stronger evidence of a causal effect on nearby firearm violence. Matching on visual similarity can improve observational injury studies involving place-based risks.
登录
查看更多内容
DOI：
10.1016/0021-9681(61)90122-9
发表时间：
1961-01-01
期刊：
JOURNAL OF CHRONIC DISEASES
影响因子：
--
作者：
HADDON, W;VALIEN, P;UMBERGER, CJ
通讯作者：
UMBERGER, CJ
DOI：
10.1016/0021-9681(62)90051-6
发表时间：
1962-01-01
期刊：
JOURNAL OF CHRONIC DISEASES
影响因子：
--
作者：
MCCARROLL, JR;HADDON, W
通讯作者：
HADDON, W
影响因子：
2
作者：
Gelman, Andrew
通讯作者：
Gelman, Andrew
影响因子：
12.7
作者：
Lipton, Robert;Yang, Xiaowen;Rura, Melissa
通讯作者：
Rura, Melissa
DOI：
10.1086/681558
发表时间：
2015-01-01
期刊：
CRIME AND JUSTICE: A REVIEW OF RESEARCH, VOL 44
影响因子：
--
作者：
MacDonald, John
通讯作者：
MacDonald, John