Abstract
Background
Nutrition plays an important role in diabetes self-management. Web-based diabetes care, driven by artificial intelligence (AI), enables more personalized care.
Objective
This study aimed to examine the usability and preliminary efficacy of a web-based AI-driven nutrition platform to support people with diabetes and their carers in identifying healthy recipes, meal planning, and web-based shopping.
Methods
Diabetes UK signposted people with diabetes and their carers to the platform’s study-specific portal through its website, social media, and newsletters. A total of 73 adult participants with prediabetes or diabetes or their carers completed the baseline web-based survey. Of these 73 participants, 23 (32%) completed a web-based survey after 8 weeks of platform use. Web-based semistructured interviews were conducted with platform users (7/23, 30%) who agreed to be followed up and diabetes experts (n=3) who had nutrition and platform knowledge. The intervention consists of a web-based platform that incorporates AI to personalize recipes, meal planning, and shopping list experiences and was made available for 8 weeks. Baseline characteristics, satisfaction, system usability, and diabetes-related and general health indicators were assessed before and after using the platform for 8 weeks.
Results
Reductions in weight (mean difference 4.5 kg/m2, 95% CI 1.0-12.0; P=.009; Cliff δ=0.33) and waist size (mean difference 3.9 cm, 95% CI 2.0-6.5; P=.008; Cliff δ=0.48) were found. Most of the participants (151/217, 69.6%) did not regularly use the platform and had low or very low engagement scores. However, the platform was perceived as accessible with no need for additional assistance (11/21, 52%), user-friendly (8/21, 38%), and easy to use (8/21, 38%), regardless of some usability issues. Saving recipes was the most popular feature, with 663 saved recipes.
Conclusions
This study indicated that the usability of the nutrition platform was well perceived by users and their carers. As participants managed their diabetes well, adding an education component would be specifically relevant for people less familiar with the role of diet in diabetes management. To assess the platform’s effectiveness in improving diabetes-related health indicators, controlled studies with a larger and more diverse participant sample are recommended.
Subject
Health Informatics,Human Factors and Ergonomics
Reference55 articles.
1. Global Economic Burden of Diabetes in Adults: Projections From 2015 to 2030
2. Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: a systematic analysis for the Global Burden of Disease Study 2017
3. Global health estimates: leading causes of deathWorld Health Organization2022-04-08https://www.who.int/data/gho/data/themes/mortality-and-global-health-estimates/ghe-leading-causes-of-death
4. The International Diabetes Federation’s guide for diabetes epidemiological studies
5. HewingsRThe cost of diabetesDiabetes UK2023-02-27https://www.researchgate.net/publication/315474818_The_cost_of_diabetes_-_report_from_Diabetes_UK
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Food Recommender System in Sub-Saharan Africa: Challenges and Prospects;Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering;2024