A Domain-Specific Retrieval-Augmented Generation Chatbot for Medical Queries on Adenomyosis and Endometriosis

Nuraisa Novia Hidayati, Luthfi Atikah
In: 2025 International Conference on Computer, Control, Informatics and its Applications (IC3INA) · 2025 · pp. 244–249 · doi:10.1109/ic3ina68387.2025.11325645 · W7123865528
article OA: closed CC0
View on OpenAlex View at publisher
⚙ AI-generated summary by claude@2026-06, 2026-06-09 ⓘ

This study developed and evaluated a domain-specific RAG chatbot for adenomyosis and endometriosis queries in Bahasa Indonesia, showing strong faithfulness and context recall but requiring retrieval refinement.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

Abstract

This study introduces a domain-specific Retrieval-Augmented Generation (RAG) chatbot for answering medical queries on adenomyosis and endometriosis in Bahasa Indonesia. The system employs a rewrite-retrieve-read paradigm, multilingual retrieval, and citation-aware generation using the Mixtral model. Document chunking was optimized for better alignment between user queries and source texts. Evaluation with the RAGAS framework yielded a faithfulness score of 72.92 and context recall of 62.09, with lower performance in answer relevancy (50.23) and context precision (44.78). These findings indicate effective grounding yet reveal the need for retrieval refinement. By adopting automated, reference-free evaluation, this work highlights both the limitations and the potential of domain-adapted RAG systems, contributing a scalable and explainable solution for medical QA in low-resource languages.

My notes (saved in your browser only)

Condition tags

endometriosisadenomyosis

Citation neighborhood

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. [ expand to 2 hops ] — adds papers reached through this work's immediate citers/citees. Heavier; up to 60 extra dots.

References (14)

Source provenance

openalex
last seen: 2026-06-04T00:00:01.174412+00:00
unpaywall
last seen: 2026-06-02T02:00:03.124865+00:00
License: CC0 · commercial use OK