Metraipolis › archive › dc_fa1a30aa2ba7
MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis — arXiv:2610.20632
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20632
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:51:59.037Z
- SHA-256 of the archived text
6e6c7a54171db205e0a88bfa3a1a10ec129f58cf52935a065a4e3b1b43f03e22- Stable URL of this page
https://metraipolis.com/documento/dc_fa1a30aa2ba7
How to cite
MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis — arXiv:2610.20632 — arXiv (en), https://arxiv.org/abs/2610.20632 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa1a30aa2ba7 (Metraipolis archive dc_fa1a30aa2ba7, sha256 6e6c7a54171db205e0a88bfa3a1a10ec129f58cf52935a065a4e3b1b43f03e22)
BibTeX
@misc{dcfa1a30aa2ba7,
title = {MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis — arXiv:2610.20632},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20632},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa1a30aa2ba7; sha256 6e6c7a54171db205e0a88bfa3a1a10ec129f58cf52935a065a4e3b1b43f03e22},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20632. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern healthcare generates increasingly complex medical reports that challenge clinical professionals in terms of time and interpretive burden. Manual review processes are slow, error-prone, and difficult to scale. This paper presents MeddeX, a Medical Report Analyzer that combines a QLoRA fine-tuned LLaMA-3 (8B) model with Retrieval-Augmented Gen eration (RAG) and a multimodal Gemini Vision layer to deliver accurate, concise, and evidence-backed summaries of medical documents. The system handles text-native PDFs, scanned image based PDFs, and direct radiological images through an intelligent hybrid extraction pipeline that includes a novel garbage-text detection mechanism for corrupted and UTF-16-encoded doc uments. Beyond single-report Q&A, MeddeX introduces report scoped retrieval for precise contextual grounding, an automated longitudinal report comparison engine, and a self-healing backfill pipeline that lazily processes legacy documents on demand. A FastAPI backend, Supabase vector store, and this http URL fron tend complete the end-to-end architecture. Evaluation against the base LLaMA3-Med42-8B model demonstrates consistent improvements across ROUGE-1 (+9.2%), ROUGE-2 (+10.0%), ROUGE-L (+11.8%), BLEU (+71.4%), and BERTScore (+0.8%), validating the benefit of domain-specific fine-tuning. MeddeX represents a practical and robust step toward AI-assisted clinical decision support. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.20632 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:47.596Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).