Hutchinson Joy M, Raffoul Amanda, Pepetone Alexandra, Andrade Lesley, Williams Tabitha E, McNaughton Sarah A, Leech Rebecca M, Reedy Jill, Shams-White Marissa M, Vena Jennifer E, Dodd Kevin W, Bodnar Lisa M, Lamarche Benoît, Wallace Michael P, Deitchler Megan, Hussain Sanaa, Kirkpatrick Sharon I
School of Public Health Sciences, University of Waterloo, Waterloo, ON, Canada.
Department of Nutritional Sciences, University of Toronto, Toronto, ON, Canada.
Br J Nutr. 2025 Mar 10;133(7):1-15. doi: 10.1017/S0007114524002587.
There is a growing focus on understanding the complexity of dietary patterns and how they relate to health and other factors. Approaches that have not traditionally been applied to characterise dietary patterns, such as latent class analysis and machine learning algorithms, may offer opportunities to characterise dietary patterns in greater depth than previously considered. However, there has not been a formal examination of how this wide range of approaches has been applied to characterise dietary patterns. This scoping review synthesised literature from 2005 to 2022 applying methods not traditionally used to characterise dietary patterns, referred to as novel methods. MEDLINE, CINAHL and Scopus were searched using keywords including latent class analysis, machine learning and least absolute shrinkage and selection operator. Of 5274 records identified, 24 met the inclusion criteria. Twelve of twenty-four articles were published since 2020. Studies were conducted across seventeen countries. Nine studies used approaches with applications in machine learning, such as classification models, neural networks and probabilistic graphical models, to identify dietary patterns. The remaining studies applied methods such as latent class analysis, mutual information and treelet transform. Fourteen studies assessed associations between dietary patterns characterised using novel methods and health outcomes, including cancer, cardiovascular disease and asthma. There was wide variation in the methods applied to characterise dietary patterns and in how these methods were described. The extension of reporting guidelines and quality appraisal tools relevant to nutrition research to consider specific features of novel methods may facilitate consistent reporting and enable synthesis to inform policies and programs.
人们越来越关注理解饮食模式的复杂性以及它们与健康和其他因素之间的关系。传统上未用于描述饮食模式的方法，如潜在类别分析和机器学习算法，可能提供比以前认为的更深入描述饮食模式的机会。然而，尚未对如何应用这一广泛的方法来描述饮食模式进行正式审查。本综述综合了2005年至2022年期间应用非传统方法（称为新方法）来描述饮食模式的文献。使用包括潜在类别分析、机器学习以及最小绝对收缩和选择算子等关键词在MEDLINE、CINAHL和Scopus数据库中进行检索。在确定的5274条记录中，有24条符合纳入标准。24篇文章中有12篇自2020年以来发表。研究在17个国家进行。9项研究使用了机器学习应用中的方法，如分类模型、神经网络和概率图形模型，来识别饮食模式。其余研究应用了潜在类别分析、互信息和小波变换等方法。14项研究评估了使用新方法描述的饮食模式与健康结果之间的关联，包括癌症、心血管疾病和哮喘。在用于描述饮食模式的方法以及这些方法的描述方式上存在很大差异。扩展与营养研究相关的报告指南和质量评估工具以考虑新方法的特定特征，可能有助于一致的报告，并能够进行综合以指导政策和计划。
