---
format: "aidr-story-markdown/v1"
id: "bb280405ef39d55c9a8eb60c0eaf94fc8bbc32e994a95d5d683105df865478c2"
canonical_url: "https://aidr.today/bb280405?lang=en"
title: "MeddeX: A Retrieval-Augmented LLaMA-3 System with Gemini Vision for Evidence-Backed Medical Report Analysis"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-16T04:00:00.000Z"
category: "Research"
topics: ["meta","llm"]
source_urls: ["https://arxiv.org/abs/2610.20632"]
summary: "MeddeX is a Medical Report Analyzer that combines a QLoRA fine-tuned LLaMA-3 (8B) model with Retrieval-Augmented Generation and a multimodal Gemini Vision layer to deliver evidence-backed summaries of medical documents. The system handles text-native PDFs, scanned image-based PDFs, and radiological images through a hybrid extraction pipeline with garbage-text detection, and includes report-scoped retrieval, automated longitudinal report comparison, and a self-healing backfill pipeline."
---

# MeddeX: A Retrieval\-Augmented LLaMA\-3 System with Gemini Vision for Evidence\-Backed Medical Report Analysis

> [Open the canonical story](<https://aidr.today/bb280405?lang=en>)

**Published:** 2026-10-16T04:00:00.000Z
**Category:** Research
**Topics:** meta, llm

## Summary

MeddeX is a Medical Report Analyzer that combines a QLoRA fine\-tuned LLaMA\-3 \(8B\) model with Retrieval\-Augmented Generation and a multimodal Gemini Vision layer to deliver evidence\-backed summaries of medical documents\. The system handles text\-native PDFs, scanned image\-based PDFs, and radiological images through a hybrid extraction pipeline with garbage\-text detection, and includes report\-scoped retrieval, automated longitudinal report comparison, and a self\-healing backfill pipeline\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.20632>)