Scholarlink

<p>Urban food landscapes significantly influence dietary habits and health outcomes, with disparities in food access contributing to obesity, particularly in socioeconomically disadvantaged neighborhoods. This study presents a data-driven approach to assess urban food landscapes using restaurant menu data from online delivery platforms in Boston, London, and Dubai. Machine learning matched menu items to the U.S. FoodData Central database, enabling the calculation of nutritional indices and neighborhood-level nutrient averages. The analysis revealed significant patterns between urban food landscapes, socioeconomic features, and obesity rates. In London and Boston, higher socioeconomic neighborhoods had better access to nutrient-rich foods, with dietary fibers showing a strong inverse association with obesity (<i>p</i> = 0.001, <i>p</i> = 0.004, respectively). In Dubai, due to limited health data, the analysis focused on food landscapes and rental prices as a proxy of a neighborhood’s socioeconomic profile. This method offers a scalable alternative to traditional food environment studies and can guide policymakers in identifying neighborhoods at risk for obesity and lack of nutritious foods. Future research should extend this method to diverse regions and advocate for standardized, open-access nutritional data to implement targeted and evidence-based nutritional interventions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Data-driven nutritional assessment of urban food landscapes: insights from Boston, London, and Dubai

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月8日

查看全文
  • Michele Tufano,
  • Fábio Duarte,
  • Martina Mazzarello,
  • Javad Eshtiyagh,
  • Carlo Ratti,
  • Guido Camps

摘要

Urban food landscapes significantly influence dietary habits and health outcomes, with disparities in food access contributing to obesity, particularly in socioeconomically disadvantaged neighborhoods. This study presents a data-driven approach to assess urban food landscapes using restaurant menu data from online delivery platforms in Boston, London, and Dubai. Machine learning matched menu items to the U.S. FoodData Central database, enabling the calculation of nutritional indices and neighborhood-level nutrient averages. The analysis revealed significant patterns between urban food landscapes, socioeconomic features, and obesity rates. In London and Boston, higher socioeconomic neighborhoods had better access to nutrient-rich foods, with dietary fibers showing a strong inverse association with obesity (p = 0.001, p = 0.004, respectively). In Dubai, due to limited health data, the analysis focused on food landscapes and rental prices as a proxy of a neighborhood’s socioeconomic profile. This method offers a scalable alternative to traditional food environment studies and can guide policymakers in identifying neighborhoods at risk for obesity and lack of nutritious foods. Future research should extend this method to diverse regions and advocate for standardized, open-access nutritional data to implement targeted and evidence-based nutritional interventions.