Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jul 21, 2024
Date Accepted: Dec 6, 2024
Patient perspectives on conversational artificial intelligence for atrial fibrillation self-management: a qualitative analysis
ABSTRACT
Background:
Conversational artificial intelligence (AI) allows for engaging interactions, however, its acceptability, barriers, and enablers to support patients with atrial fibrillation (AF) are unknown.
Objective:
This work stems from the Coordinating Health care with Artificial intelligence–supported Technology for patients with Atrial Fibrillation (CHAT-AF) trial and aims to explore patient perspectives on receiving a conversational AI support program.
Methods:
Patients with AF recruited for the randomised controlled trial and received the intervention were approached for semi-structured interviews using purposive sampling. The six-month intervention consisted of fully automated conversational AI phone calls (with speech recognition and natural language processing) that assessed patient health, and provided self-management support and education. Interviews were recorded, transcribed, and thematically analysed.
Results:
We conducted 30 interviews (mean age 65.4 years [SD 11.9]; 70% male). Four themes were identified: (1) Interaction with a voice-based conversational AI program (human-like interactions, restriction to prespecified responses, trustworthiness of hospital-delivered conversational AI); (2) Engagement is influenced by the personalisation of content, delivery mode and frequency (tailoring to own health context, interest in novel information regarding health, overwhelmed with large volumes of information, flexibility provided by multichannel delivery); (3) Improving access to AF care and information (continuity in support, enhancing access to health-related information); (4) Empowering patients to better self-manage their AF (encouraging healthy habits through frequent reminders, reassurance from rhythm monitoring devices).
Conclusions:
Whilst conversational AI was described as an engaging way to receive education and self-management support, improvements such as enhanced dialogue flexibility to allow for more naturally flowing conversations and tailoring to patient health context were also mentioned. Clinical Trial: Australian New Zealand Clinical Trials Registry (ACTRN12621000174886)
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.