EUVIMEDEUVIMED entdecken
Open Access

MedDiscover: A Domain-Specific Retrieval-Augmented Generation Framework for Evidence-Grounded Knowledge Extraction in Metabolomics

Vatsal Pravinbhai Patel iD, Elena Jolkver iD, Anne Schwerk iD

Computational and Structural Biotechnology Journal · 01.03.2026 · 35 (1)

DOI: 10.34133/csbj.0018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 09.04.2026. Verfasst von Vatsal Pravinbhai Patel und 2 weiteren Autor:innen. Beteiligte Einrichtung: IU Internationale Hochschule GmbH, 99084 Erfurt, Germany. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrieval-augmented generation (RAG) can improve biomedical question answering, but claims about domain-specific retrievers require transparent, reproducible evaluation. We present MedDiscover, an open-source RAG implementation and benchmark instantiated for metabolomics and metabolic-disorder literature, with a 2-tier dataset design: a Gold set of 10 papers and 30 expert-curated question–answer (QA) pairs with traceable references, and a Silver set of 100 papers curated using International Statistical Classification of Diseases and Related Health Problems 10th Revision metabolic disorder codes E70 to E88 with ~600 synthetic QA pairs and retrievability metadata (Ada n = 300, MedCPT n = 300). On the Gold set, retrieval augmentation improves grounding compared with a non-RAG baseline. On the Silver benchmark, MedCPT and Ada show comparable retrieval-centric performance (faithfulness P = 0.85 , context recall P = 0.50 , context precision P = 0.49 , and answer relevancy P = 0.82 ), while MedCPT yields higher answer correctness (Mann–Whitney U P = 5.72 × 10 − 11 , Cliff’s δ = 0.303 , and common-language effect = 0.651 ). We release code, evaluation scripts, and document lists to support reproducibility.

Autor:innen und Institutionen

  • IU Internationale Hochschule GmbH, 99084 Erfurt, Germany.

ORCID-Profile: Vatsal Pravinbhai Patel, Elena Jolkver, Anne Schwerk

Zitieren

APA

Patel, V. P., Jolkver, E., & Schwerk, A. (2026). MedDiscover: A Domain-Specific Retrieval-Augmented Generation Framework for Evidence-Grounded Knowledge Extraction in Metabolomics. Computational and Structural Biotechnology Journal, 35(1). https://doi.org/10.34133/csbj.0018

Vancouver

Patel VP, Jolkver E, Schwerk A. MedDiscover: A Domain-Specific Retrieval-Augmented Generation Framework for Evidence-Grounded Knowledge Extraction in Metabolomics. Computational and Structural Biotechnology Journal. 2026;35(1). doi:10.34133/csbj.0018

BibTeX
@article{Patel2026,
  author = {Patel, Vatsal Pravinbhai and Jolkver, Elena and Schwerk, Anne},
  title = {MedDiscover: A Domain-Specific Retrieval-Augmented Generation Framework for Evidence-Grounded Knowledge Extraction in Metabolomics},
  journal = {Computational and Structural Biotechnology Journal},
  year = {2026},
  volume = {35},
  number = {1},
  doi = {10.34133/csbj.0018}
}
Kostenlos starten →