Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Human Factors

Date Submitted: Nov 4, 2022
Date Accepted: Apr 15, 2023

The final, peer-reviewed published version of this preprint can be found here:

Usability and Preliminary Efficacy of an Artificial Intelligence–Driven Platform Supporting Dietary Management in Diabetes: Mixed Methods Study

Bul K, Holliday N, Bhuiyan MRA, Clark C, Allen J, Wark P

Usability and Preliminary Efficacy of an Artificial Intelligence–Driven Platform Supporting Dietary Management in Diabetes: Mixed Methods Study

JMIR Hum Factors 2023;10:e43959

DOI: 10.2196/43959

PMID: 37556198

PMCID: 10448291

Usability and preliminary efficacy of an AI-driven platform supporting dietary management in diabetes: A mixed-method study

  • Kim Bul; 
  • Nikki Holliday; 
  • Mohammad Rashed Alam Bhuiyan; 
  • Cain Clark; 
  • John Allen; 
  • Petra Wark

ABSTRACT

Background:

Nutrition plays an important role in diabetes self-management. Online diabetes care, driven by Artificial Intelligence, enables more personalized care.

Objective:

This study aims to examine the usability and preliminary efficacy of an online Artificial Intelligence driven 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 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:

Reductions in weight (MeanDiff: 4.5 kg/m2, 95% CI [1.0, 12.0], P=.009, Cliff's ∂ =0.33) and waist size (MeanDiff: 3.9 cm, 95% CI [2.0, 6.5], P=.008, Cliff's ∂ =0.48) were found. Most participants (60.6%) 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 (52%), user-friendly (38%), and easy to use (38%) regardless of some usability issues. Saving recipes was the most popular feature with a total of 663 saved recipes.

Conclusions:

This study indicated that the usability of the nutrition platform was well-perceived by its users and their carers. 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. Clinical Trial: Not applicable.


 Citation

Please cite as:

Bul K, Holliday N, Bhuiyan MRA, Clark C, Allen J, Wark P

Usability and Preliminary Efficacy of an Artificial Intelligence–Driven Platform Supporting Dietary Management in Diabetes: Mixed Methods Study

JMIR Hum Factors 2023;10:e43959

DOI: 10.2196/43959

PMID: 37556198

PMCID: 10448291

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.