探索森林而非树木：一种定义致肥胖和抗肥胖环境的创新方法。
Exploring the forest instead of the trees: An innovative method for defining obesogenic and obesoprotective environments.
作者信息
Nau Claudia, Ellis Hugh, Huang Hongtai, Schwartz Brian S, Hirsch Annemarie, Bailey-Davis Lisa, Kress Amii M, Pollak Jonathan, Glass Thomas A
机构信息
Johns Hopkins Bloomberg School of Public Health Global Obesity Prevention Center, 615 N Wolfe Street, Baltimore, MD 21205, USA.
Johns Hopkins Bloomberg School of Public Health Global Obesity Prevention Center, 615 N Wolfe Street, Baltimore, MD 21205, USA; Johns Hopkins Whiting School of Engineering, 3400 North Charles Street, Baltimore, MD 21218, USA.
出版信息
Health Place. 2015 Sep;35:136-46. doi: 10.1016/j.healthplace.2015.08.002. Epub 2015 Sep 19.
Past research has assessed the association of single community characteristics with obesity, ignoring the spatial co-occurrence of multiple community-level risk factors. We used conditional random forests (CRF), a non-parametric machine learning approach to identify the combination of community features that are most important for the prediction of obesogenic and obesoprotective environments for children. After examining 44 community characteristics, we identified 13 features of the social, food, and physical activity environment that in combination correctly classified 67% of communities as obesoprotective or obesogenic using mean BMI-z as a surrogate. Social environment characteristics emerged as most important classifiers and might provide leverage for intervention. CRF allows consideration of the neighborhood as a system of risk factors.
过去的研究评估了单一社区特征与肥胖之间的关联，而忽略了多种社区层面风险因素的空间共现情况。我们使用条件随机森林（CRF）这一非参数机器学习方法，来确定对于预测儿童致肥胖和防肥胖环境最为重要的社区特征组合。在考察了44个社区特征后，我们确定了社会、食物和身体活动环境的13个特征，这些特征结合起来，以平均BMI-z作为替代指标，可将67%的社区正确分类为防肥胖或致肥胖社区。社会环境特征成为最重要的分类指标，可能为干预提供着力点。CRF能够将邻里社区视为一个风险因素系统加以考量。
Zotero 插件