MétaCan
Menu
Back to cohort
Record W4410530765 · doi:10.2196/70409

Exploring the Acceptance and Opportunities of Using a Specific Generative AI Chatbot to Assist Parents in Managing Pediatric Rheumatological Chronic Health Conditions: Mixed Methods Study

2025· article· en· W4410530765 on OpenAlexvenueno aff
Cheryl K. Lau, Klaudia Kupiec, Polly Livermore

Bibliographic record

VenueJMIR Pediatrics and Parenting · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsnot available
FundersVersus Arthritis
KeywordsPreprintChatbotMedicineArtificial intelligenceComputer scienceWorld Wide Web

Abstract

fetched live from OpenAlex

Background: Health care chatbots can be used to support patients and their families with everyday decision-making. While there is some research on integrating artificial intelligence into pediatric care, no study has focused on the opportunity of implementing a generative artificial intelligence chatbot for pediatric rheumatology. Pediatric rheumatology conditions require intense family input, which can often leave families struggling to navigate disease flares, pain, fatigue, medication side effects and adherence, and support of their child, often when pediatric rheumatology departments are shut. Understanding how we can support families better, without the need for increased personnel, will have implications for the health care systems. Objective: The study aimed to explore parental and children and young people's acceptance of chatbot use in a pediatric context, and understand how a chatbot could be specifically used for managing a child's chronic health condition. Methods: This study was a mixed methods design, using both a family workshop and a subsequent questionnaire. Results: In total, 22 participants contributed to the qualitative design using the world café methodology at a workshop, and 47 participants (36 parents and 11 children and young people) completed quantitative data via a questionnaire. Participants expressed their likelihood of using chatbot technology, including ChatGPT, due to its accessibility. However, participants had significantly greater intention (parents: P<.001; children and young people: P=.006) to use a specific chatbot over ChatGPT, due to increased trust, credibility, and specificity in design. Children and young people and parents should be distinguished as 2 user groups in chatbot design, reflecting their specific needs in chatbot features and personalization. Conclusions: Overall, the study reinforced the need for a specialized and trusted chatbot designed with input from health professionals to assist families in managing complex chronic health conditions to support families in between appointments and complement existing face-to-face care. Future research should evaluate users' engagement with a functional prototype to investigate its usefulness and explore its implementation into families' everyday lives. Importantly, the current findings have broader implications for the field of pediatric health care, as similarly tailored chatbot interventions could benefit families who are managing other chronic health conditions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.025
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.019
Threshold uncertainty score0.101

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0190.025
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0020.001
Scholarly communication0.0030.002
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.275
GPT teacher head0.485
Teacher spread0.210 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designQualitative
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations6
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Pediatrics and ParentingSame topicDigital Mental Health InterventionsFrench-language works237,207