Evidence map›Paper›PMID 40073398›Full record

Trial reportJournal of medical Internet research2025

Patient Perspectives on Conversational Artificial Intelligence for Atrial Fibrillation Self-Management: Qualitative Analysis.

Ritu Trivedi, Tim Shaw, Brodie Sheahen, Clara K Chow, Liliana Laranjo

Abstract readMulticenter StudyRandomized Controlled Trial
PubMed Full text at PMC Publisher
In one paragraph

Trial report in Journal of medical Internet research, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 9 papers, 3 of them syntheses that pooled it.

0numbers the graph read from it
0cells of the map it votes in
9citing papers in PubMed, 3 pooled it
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

9 citing papers in PubMed, 3 syntheses or guidelines pooled it.

  1. Pooled it
  2. Pooled it
  3. Pooled it
  4. Trial
  5. Trial
  6. Review
  7. Article
  8. Article
  9. Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

5 authors.

Ritu TrivediWestmead Applied Research Centre, Faculty of Medicine and Health, The University of Sydney, Westmead, Australia.ORCID https://orcid.org/0000-0002-5128-3202
Tim ShawWestmead Applied Research Centre, Faculty of Medicine and Health, The University of Sydney, Westmead, Australia.ORCID https://orcid.org/0000-0003-0783-1918
Brodie SheahenWestmead Applied Research Centre, Faculty of Medicine and Health, The University of Sydney, Westmead, Australia.ORCID https://orcid.org/0009-0003-0110-5402
Clara K ChowWestmead Applied Research Centre, Faculty of Medicine and Health, The University of Sydney, Westmead, Australia.ORCID https://orcid.org/0000-0003-4693-0038
Liliana LaranjoWestmead Applied Research Centre, Faculty of Medicine and Health, The University of Sydney, Westmead, Australia.ORCID https://orcid.org/0000-0003-1020-3402

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

backgroundConversational artificial intelligence (AI) allows for engaging interactions, however, its acceptability, barriers, and enablers to support patients with atrial fibrillation (AF) are unknown.

objectiveThis work stems from the Coordinating Health care with AI-supported Technology for patients with AF (CHAT-AF) trial and aims to explore patient perspectives on receiving support from a conversational AI support program.

methodsPatients with AF recruited for a randomized controlled trial who received the intervention were approached for semistructured interviews using purposive sampling. The 6-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 analyzed.

resultsWe conducted 30 interviews (mean age 65.4, SD 11.9 years; 21/30, 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 personalization 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).

conclusionsAlthough 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.

trial registrationAustralian New Zealand Clinical Trials Registry ACTRN12621000174886; https://tinyurl.com/3nn7tk72. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/34470.

Indexed as

Artificial IntelligenceAtrial FibrillationCommunicationSelf-ManagementAgedFemaleHumansInterviews as TopicMaleMiddle AgedQualitative Researchatrial fibrillationconversational agentsconversational artificial intelligencedigital healthpatient perspectivequalitative researchself-managementspeech recognition

Identifiers

PMID40073398
PMCPMC11947624

What Socratic holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.