{
  "id": 9735,
  "url": "https://doi.org/10.1038/s41746-025-01519-z",
  "title": "Retrieval augmented generation for 10 large language models and its generalizability in assessing medical fitness",
  "summary": "Large Language Models (LLMs) hold promise for medical applications but often lack domain-specific expertise. Retrieval Augmented Generation (RAG) enables customization by integrating specialized knowledge. This study assessed the accuracy, consistency, and safety of LLM-RAG models in determining surgical fitness and delivering preoperative instructions using 35 local and 23 international guidelines. Ten LLMs (e.g., GPT3.5, GPT4, GPT4o, Gemini, Llama2, and Llama3, Claude) were tested across 14 cl",
  "authors": "Yu He Ke, Liyuan Jin, Kabilan Elangovan, Hairil Rizal Abdullah, Nan Liu, Alex Tiong Heng Sia",
  "category": "research",
  "topics": "healthcare",
  "orgs": "google,meta",
  "regions": null,
  "published_at": "2025-04-05T00:00:00.000Z",
  "fetched_at": "2026-07-14T16:34:00.820Z",
  "source_slug": "openalex",
  "source_name": "OpenAlex",
  "source_homepage": "https://openalex.org",
  "ethics_ai_record_url": "https://ethics.ai/record/9735",
  "original_url": "https://doi.org/10.1038/s41746-025-01519-z",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}