Computer Science Department, University of Jaén, 23007 Jaén, Spain.
Computer Science Department, University of Ciego de Ávila, Ciego de Ávila 65100, Cuba.
Int J Environ Res Public Health. 2023 Feb 27;20(5):4248. doi: 10.3390/ijerph20054248.
Recommender systems are currently a relevant tool for facilitating access for online users, to information items in search spaces overloaded with possible options. With this goal in mind, they have been used in diverse domains such as e-commerce, e-learning, e-tourism, e-health, etc. Specifically, in the case of the e-health scenario, the computer science community has been focused on building recommender systems tools for supporting personalized nutrition by delivering user-tailored foods and menu recommendations, incorporating the health-aware dimension to a larger or lesser extent. However, it has been also identified the lack of a comprehensive analysis of the recent advances specifically focused on food recommendations for the domain of diabetic patients. This topic is particularly relevant, considering that in 2021 it was estimated that 537 million adults were living with diabetes, being unhealthy diets a major risk factor that leads to such an issue. This paper is centered on presenting a survey of food recommender systems for diabetic patients, supported by the PRISMA 2020 framework, and focused on characterizing the strengths and weaknesses of the research developed in this direction. The paper also introduces future directions that can be followed in the next future, for guaranteeing progress in this necessary research area.
推荐系统是目前一种方便在线用户访问搜索空间中信息的有效工具，该搜索空间中充满了各种可能的选项。基于这一目标，推荐系统已经在电子商务、电子学习、电子旅游、电子健康等不同领域得到了应用。具体来说，在电子健康的场景中，计算机科学界一直致力于构建推荐系统工具，通过提供用户定制的食物和菜单推荐来支持个性化营养，在不同程度上纳入健康感知维度。然而，人们也发现，缺乏对专门针对糖尿病患者的食物推荐领域的最新进展进行全面分析。考虑到 2021 年估计有 5.37 亿成年人患有糖尿病，不健康的饮食是导致这一问题的主要风险因素，因此这个话题尤为重要。本文围绕着糖尿病患者的食物推荐系统进行了调查，调查工作以 PRISMA 2020 框架为支撑，侧重于描述在这一方向上开展的研究的优缺点。本文还介绍了未来的发展方向，以确保在这一必要的研究领域取得进展。
