Metraipolis › archive › dc_720915f3bbda

Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance — arXiv:2610.33279

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33279
License (as archived): CC0-1.0
Archived: 2026-10-27T08:11:12.356Z
SHA-256 of the archived text: fd9231e5bef2e84cbf1677b2cab6e01c37c0418796a053918037b19a0005c3a0
Stable URL of this page: https://metraipolis.com/documento/dc_720915f3bbda

How to cite

Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance — arXiv:2610.33279 — arXiv (en), https://arxiv.org/abs/2610.33279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_720915f3bbda (Metraipolis archive dc_720915f3bbda, sha256 fd9231e5bef2e84cbf1677b2cab6e01c37c0418796a053918037b19a0005c3a0)

BibTeX

@misc{dc720915f3bbda,
  title = {Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance — arXiv:2610.33279},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33279},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_720915f3bbda; sha256 fd9231e5bef2e84cbf1677b2cab6e01c37c0418796a053918037b19a0005c3a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Introduction: Increasing volumes of individual case safety reports (ICSRs) challenge expert-led causality assessment in pharmacovigilance. We developed MARCA (Multi-Agent Retrieval-Augmented Causality Assessment), a four-agent framework for Naranjo-based assessment, and evaluated agreement with human experts and exploratory differences between non-RAG and RAG-labelled scores. Methods: MARCA combined scientific literature retrieval, drug-label assessment, objective-evidence classification, and clinical causality reasoning using Gemini 2.5 Pro and DeepSeek-V3.2. Agent-generated rationales informed human-assisted scoring. A consensus expert reference standard covered 215 ICSRs and 1,562 drug-event combinations (DECs) from FAERS (Q1-Q2 2025). Agreement was measured using percentage agreement and Cohen's kappa. Results: Question-level agreement was 96.8% for Naranjo Q2 (kappa = 0.491; 95% CI 0.265-0.663), 85.4% for Q5 (kappa = 0.269; 95% CI 0.180-0.340), and 96.8% for Q10 (kappa = 0.922; 95% CI 0.885-0.951). Final causality classification agreement was 79.4% (95% CI 71.8-85.3; kappa = 0.587, 95% CI 0.450-0.690). In a retrospective subset of 60 DECs, agreement was higher for RAG-labelled than non-RAG scores for Q5 (83.3% vs 65.0%) and Q10 (100.0% vs 18.3%). Discussion: MARCA-assisted assessment showed substantial variation in agreement across Naranjo questions, with lower concordance for alternative causes. Retrospective RAG comparisons are exploratory and do not establish prospective effectiveness.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.33279 — 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 2026-10-27T07:56:00.188Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).