Currently submitted to: JMIR Formative Research
Date Submitted: Apr 6, 2026
Open Peer Review Period: Apr 7, 2026 - Jun 2, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Developing an AI-based Chatbot for Community Antibiotic Usage Data Collection in LMICs: a proof-of-concept study in Thailand
ABSTRACT
Background:
Antibiotic consumption is a key driver of antimicrobial resistant (AMR) infections, and the majority of usage is outside of hospital settings in low- and middle-income countries (LMICs), but we know remarkably little about usage patterns and drivers. The lack of reliable data poses challenges for establishing targets, understanding AMR burden and designing and evaluating interventions.
Objective:
This study aimed to design and develop an AI-based chatbot for the collection of community antibiotic usage data in Thailand.
Methods:
The study employed a proof-of-concept design, developing CHATSCi-AMI with GPT-4o-mini on the LINE platform. Internal testing involved 35 MORU staff, using a chatbot pipeline (Dify.ai, ChatBean, REDCap) for demographic, medication, and knowledge data collection. Web scraping with BeautifulSoup and AI summarisation structured data, with a simulated dataset (50 users, 12 weeks) analysed for misuse patterns (e.g., 64.4% inappropriate use).
Results:
CHATSCi-AMI successfully integrated with LINE, achieving stable functionality in testing, with rich menus and image recognition for antibiotic identification. The simulated dataset revealed 64.4% inappropriate antibiotic use (95% CI: 50.2–78.6%, p<0.01), highlighting misuse trends. User feedback (n=35) indicated high satisfaction (80% rated usability ≥4/5), though technical errors occurred in 5% of interactions.
Conclusions:
CHATSCi-AMI demonstrates feasibility for scalable AMR surveillance in LMICs, offering a novel approach with longitudinal data collection and AI structuring. Future work post-OxTREC approval should focus on real-world data and enhanced privacy measures to support public health policy and individual monitoring.
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.