{
  "abstract": "Background: Diabetic retinopathy (DR) is the leading cause of preventable blindness in working-age adults, yet scalable early detection is limited by the unreliability of AI-assisted screening. Multimodal large language models can interpret fundus photographs and support DR grading, but they frequently hallucinate - fabricating lesions or misclassifying referable DR - which directly threatens timely treatment and prevention of vision loss. We developed HalluciGuard-Eye to make AI-assisted DR assessment trustworthy.\n\nMethods: HalluciGuard-Eye combines knowledge graph-enhanced retrieval-augmented generation with hierarchical hallucination detection. An Ophthalmic Clinical Knowledge Graph containing 47,832 medical entities and 156,294 semantic relationships was constructed from clinical guidelines and published literature. A dual-stream architecture uses a Visual-Semantic Alignment Module to verify cross-modal consistency and a Clinical Factuality Grounding Network to anchor generated content to reranked evidence. The Hierarchical Factuality Score assesses anatomical, pathological, and clinical-recommendation accuracy. The framework was evaluated on four public ophthalmic imaging benchmarks.\n\nResults: HalluciGuard-Eye reduced hallucination rates by 42.2% compared with state-of-the-art medical multimodal large language models and achieved 91.6% factual accuracy for clinical entity recognition on EyePACS. For diabetic retinopathy grading, sensitivity was 89.6% and specificity was 92.1%, representing improvements of 2.4% and 2.7%, respectively, over MedRAG. In the component ablation, removing knowledge-graph retrieval lowered EyePACS HFS by 9.4 percentage points. Additional analyses yielded 87.6% critical-evidence recall@20, 89.2% lesion-location accuracy, and 88.9% sensitivity in a patient-clustered cohort.\n\nConclusions: These results indicate that knowledge-grounded retrieval and hierarchical factuality assessment can reduce hallucinations while preserving diagnostic performance in ophthalmic multimodal language models.",
  "abstract_shown": true,
  "affiliations": [
    "Ophthalmic Center, The Second Affiliated Hospital, Jiangxi Medical College, Nanchang University"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Ge Wu"
    },
    {
      "affs": [
        0
      ],
      "name": "Chong Ai"
    },
    {
      "affs": [
        0
      ],
      "name": "Weiqi Wu"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/e7a0tmz7z9w9b.bib",
  "cited_by": 0,
  "doi": "10.3389/fendo.2026.1976190",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13727480/?tool=EBI",
  "id": "e7a0tmz7z9w9b",
  "issns": [
    "1664-2392"
  ],
  "landing_url": "https://www.frontiersin.org/articles/10.3389/fendo.2026.1976190/full",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Original Research"
    ],
    [
      "openalex",
      "1707|Multimodal Machine Learning Applications"
    ]
  ],
  "openalex": "W7223056845",
  "pdf_url": "https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2026.1976190/pdf",
  "pmcid": "PMC13727480",
  "pmid": "42978596",
  "published": "2026-10-20",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/e7a0tmz7z9w9b.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:20Z",
      "native_id": "10.3389/fendo.2026.1976190",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fendo.2026.1976190/full"
    },
    {
      "first_seen": "2026-11-04T15:20:45Z",
      "native_id": "PMC:PMC13727480",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13727480"
    },
    {
      "first_seen": "2026-11-06T12:23:21Z",
      "native_id": "PMC13727480",
      "source": "pmc",
      "url": "https://doi.org/10.3389/fendo.2026.1976190"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:1664-2392",
      "subfield": "endocrinology-metabolism"
    }
  ],
  "title": "HalluciGuard-eye: knowledge graph-enhanced retrieval-augmented generation for hallucination detection and mitigation in ophthalmic multimodal large language models",
  "title_text": "HalluciGuard-eye: knowledge graph-enhanced retrieval-augmented generation for hallucination detection and mitigation in ophthalmic multimodal large language models",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T12:20:39Z",
  "url": "https://research.draconitic.com/paper/e7a0tmz7z9w9b",
  "venue": "Frontiers in Endocrinology",
  "versions": []
}