{"slug": "multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in", "title": "Multi-Agent Retrieval-Augmented Causality Assessment (MARCA) of Individual Case Safety Reports in Pharmacovigilance", "summary": "A four-agent framework called MARCA, built on Gemini 2.5 Pro and DeepSeek-V3.2, reached 79.4% final causality classification agreement (kappa = 0.587, 95% CI 0.450-0.690) with a consensus expert reference standard across 215 individual case safety reports and 1,562 drug-event combinations from FAERS for Q1-Q2 2025, according to an arXiv paper (2610.33279v1). Question-level agreement ranged from 85.4% for Naranjo Q5 (kappa = 0.269) to 96.8% for Q2 (kappa = 0.491) and Q10 (kappa = 0.922), with the authors reporting lower concordance on alternative causes. In a retrospective subset of 60 drug-event combinations, RAG-labelled scores agreed more often than non-RAG scores for Q5 (83.3% vs 65.0%) and Q10 (100.0% vs 18.3%), a comparison the authors call exploratory and insufficient to establish prospective effectiveness.", "body_md": "arXiv:2610.33279v1 Announce Type: new \nAbstract: 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.\n  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.\n  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%).\n  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.", "url": "https://wpnews.pro/news/multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in", "canonical_source": "https://www.machinebrief.com/news/multi-agent-retrieval-augmented-causality-assessment-marca-o-rm8w", "published_at": "2026-10-27 04:00:00+00:00", "updated_at": "2026-10-27 04:41:53.755668+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models"], "entities": ["MARCA", "Gemini 2.5 Pro", "DeepSeek-V3.2", "FAERS", "Naranjo"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in", "markdown": "https://wpnews.pro/news/multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in.md", "text": "https://wpnews.pro/news/multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in.txt", "jsonld": "https://wpnews.pro/news/multi-agent-retrieval-augmented-causality-assessment-marca-of-individual-case-in.jsonld"}}