EUVIMEDEUVIMED entdecken
FallberichtOpen Access · CC BY 4.0

A Fine-Tuned Multi-Agent Large Language Model Platform with Retrieval-Augmented Generation for Clinical Case Report Analysis

Mateusz Walo, Dariusz Majerek, Izolda Gorgol

Applied Sciences · 11.11.2026 · 16 (22) · 11184

DOI: 10.3390/app162211184 ↗

Kurz gefasst

Fallbericht in der Zeitschrift Applied Sciences, online erschienen am 11.11.2026. Verfasst von Mateusz Walo und 2 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lublin University of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a prototype for the structured analysis of PubMed case-report titles, keywords and abstracts, combining domain fine-tuning, retrieval-augmented generation (RAG) and five specialist-role agents with a synthesis agent. DeepSeek-R1-Distill-Qwen-7B was fine-tuned using QLoRA on 8999 reports with teacher-generated targets. The retrieval index contains 7679 chunks from 13 medical sources. On 501 held-out reports, symmetric final-answer-only scoring, with missing final answers assigned zero, showed increases after fine-tuning in ROUGE-1 (+0.0253, 95% CI +0.0107 to +0.0394) and structural completeness (+0.0371, +0.0160 to +0.0579). The mean BERTScore difference was +0.0035 (−0.0085 to +0.0153), providing inconclusive evidence of a mean improvement. Among the tested platform configurations, retrieval showed no clear benefit on the reported final-answer reference metrics, and the specialist panel scored below a single structured agent. Final-answer results for the full platform versus the model alone were mixed. The full platform used 11.7 times as many tokens and 5.9 times the latency of the fine-tuned model alone. A blinded LLM-as-a-judge audit of 1941 statements found that 20–24% were unsupported or contradicted by the supplied sources; among checkable factual statements, this proportion was 24.5–28.5%. Different report requirements and a shared 1024-token generation limit constrain component-level interpretation. The results concern the evaluated configurations, reference similarity, format and source agreement; they do not establish improved diagnostic accuracy or clinical safety.

Förderung

  • Lublin University of Technology

Zitieren

APA

Walo, M., Majerek, D., & Gorgol, I. (2026). A Fine-Tuned Multi-Agent Large Language Model Platform with Retrieval-Augmented Generation for Clinical Case Report Analysis. Applied Sciences, 16(22), 11184. https://doi.org/10.3390/app162211184

Vancouver

Walo M, Majerek D, Gorgol I. A Fine-Tuned Multi-Agent Large Language Model Platform with Retrieval-Augmented Generation for Clinical Case Report Analysis. Applied Sciences. 2026;16(22):11184. doi:10.3390/app162211184

BibTeX
@article{Walo2026,
  author = {Walo, Mateusz and Majerek, Dariusz and Gorgol, Izolda},
  title = {A Fine-Tuned Multi-Agent Large Language Model Platform with Retrieval-Augmented Generation for Clinical Case Report Analysis},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {22},
  pages = {11184},
  doi = {10.3390/app162211184}
}
Kostenlos starten →