TY - UNPB
T1 - Usability and preliminary efficacy of an AI-driven platform supporting dietary management in diabetes: A mixed-method study
AU - Bul, Kim
AU - Holliday, Nikki
AU - Bhuiyan, Mohammad Rashed Alam
AU - Clark, Cain
AU - Allen, John
AU - Wark, Petra
PY - 2022/11/21
Y1 - 2022/11/21
N2 - Background: Nutrition plays an important role in diabetes self-management. Providing aspects of diabetes care online using Artificial Intelligence and deep learning enables more personalized care. Objective: This study aims to examine the usability and preliminary efficacy of an online nutrition platform to support people with diabetes and their carers in identifying healthy recipes, meal planning, and online shopping. Methods: Diabetes UK signposted people with diabetes and their carers through their website, social media and newsletters. Seventy-three adult participants with (pre)diabetes or their carers, completed the baseline online survey, as did 23 of these after 8 weeks of platform use. Online semi-structured interviews were performed with platform users (n=7) who agreed to be followed-up and diabetes experts (n=3) who had nutrition and/or platform knowledge. The intervention consists of an online platform, incorporating Artificial Intelligence and deep learning to personalize recipes, meal planning and shopping list experiences, and was made available for a period of 8 weeks. Baseline characteristics, satisfaction, system usability, and (diabetes-related) health indicators were assessed before and after 8 weeks of platform use. Results: Improvements in weight (MeanDiff: 4.5 kg/m2, 95% CI [1.0, 12.0], p=0.009, d=0.51 95% CI [0.07, 0.94]) and waist size (MeanDiff: 3.9 cm, 95% CI [2.0, 6.5], p=0.008, d=0.80 95% CI [0.24, 1.34]) were found. Most participants did not regularly use the platform but perceived it as accessible, user-friendly, and easy to use with some usability issues. Saving recipes was the most popular feature. Conclusions: This study indicated that the usability of the nutrition platform was well-perceived by its diabetes users for recipe inspiration, an area supported by Artificial Intelligence and deep learning. Because participants managed their diabetes well, adding in education 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.
AB - Background: Nutrition plays an important role in diabetes self-management. Providing aspects of diabetes care online using Artificial Intelligence and deep learning enables more personalized care. Objective: This study aims to examine the usability and preliminary efficacy of an online nutrition platform to support people with diabetes and their carers in identifying healthy recipes, meal planning, and online shopping. Methods: Diabetes UK signposted people with diabetes and their carers through their website, social media and newsletters. Seventy-three adult participants with (pre)diabetes or their carers, completed the baseline online survey, as did 23 of these after 8 weeks of platform use. Online semi-structured interviews were performed with platform users (n=7) who agreed to be followed-up and diabetes experts (n=3) who had nutrition and/or platform knowledge. The intervention consists of an online platform, incorporating Artificial Intelligence and deep learning to personalize recipes, meal planning and shopping list experiences, and was made available for a period of 8 weeks. Baseline characteristics, satisfaction, system usability, and (diabetes-related) health indicators were assessed before and after 8 weeks of platform use. Results: Improvements in weight (MeanDiff: 4.5 kg/m2, 95% CI [1.0, 12.0], p=0.009, d=0.51 95% CI [0.07, 0.94]) and waist size (MeanDiff: 3.9 cm, 95% CI [2.0, 6.5], p=0.008, d=0.80 95% CI [0.24, 1.34]) were found. Most participants did not regularly use the platform but perceived it as accessible, user-friendly, and easy to use with some usability issues. Saving recipes was the most popular feature. Conclusions: This study indicated that the usability of the nutrition platform was well-perceived by its diabetes users for recipe inspiration, an area supported by Artificial Intelligence and deep learning. Because participants managed their diabetes well, adding in education 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.
U2 - 10.2196/preprints.43959
DO - 10.2196/preprints.43959
M3 - Preprint
SP - 1
BT - Usability and preliminary efficacy of an AI-driven platform supporting dietary management in diabetes: A mixed-method study
PB - JMIR Publications
ER -
