Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Sep 4, 2022
Open Peer Review Period: Sep 4, 2022 - Oct 30, 2022
Date Accepted: Oct 12, 2023
(closed for review but you can still tweet)
Development of a virtual human for supporting tobacco cessation during the COVID-19 pandemic: A viewpoint
ABSTRACT
Background:
People who smoke tobacco are at greater risk of developing severe COVID-19. Moreover, the COVID-19 pandemic has reduced the accessibility of smoking cessation services globally. Innovations are needed to support smoking cessation care during the pandemic. Virtual humans are artificially intelligent computer agents with a hyperrealistic, humanlike appearance. Virtual humans may be a scalable and engaging way to deliver smoking cessation support. Florence, a virtual human health worker, was developed in collaboration with the World Health Organization (WHO) to support people towards tobacco cessation. Florence provides evidence-based information, assists with making quit plans, and directs people to WHO-recommended cessation services in their country.
Objective:
This study aimed to: (1) describe the development of Florence, a virtual health worker for tobacco cessation; and (2) conduct a preliminary user evaluation of the virtual health worker, the program content, and the effects on making quit attempts.
Methods:
115 users from 49 unique countries (lower-middle income: 50 of 115, 43.5%; high-income: 49 of 115, 42.6%; upper-middle income: 16 of 115, 12.9%; low-income 0 of 115, 0.0%) participated in an anonymous online survey following an interaction with the English version of Florence. They completed 1-item self-report scales on the quality of the user experience, information and advice, and whether Florence helped with making a quit plan and influenced behavioral intent to try the recommended services. Open-ended qualitative feedback was collected about the virtual health worker and analysed using reflexive thematic analysis.
Results:
Analyses revealed promising results. On average, participants reported having a good interaction experience with Florence (M=3.17/ 4, SD=0.81). They perceived that she provided good information and advice (M=3.21/ 4, SD=0.92). Most respondents reported that Florence helped or maybe helped them to make a quit plan (yes: 50 of 114, 43.5%; maybe: 37 of 114, 32.5%; probably not: 12 of 114, 10.5%; no: 15 of 114, 13.2%), and that they planned to try the tobacco cessation services she recommended (yes: 50 of 112, 43.5%; maybe: 49 of 112, 42.6%; probably not: 9 of 112, 8.0%). Very few participants were not willing to try the services recommended by Florence (4 of 112; 3.5%). Qualitative data revealed Florenceās strengths (informative, sense of connection, clear communication, useful) and areas to improve in the future (aspects of the virtual human design, cessation program, and interface).
Conclusions:
Virtual health workers are a promising innovation to expand the reach of tobacco cessation information and support during the COVID-19 pandemic. Further trials are needed to evaluate the acceptability and effectiveness of Florence at reducing tobacco use in diverse populations. Clinical Trial: Not applicable.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.