{
  "abstract": "Objectives: To evaluate whether large language model assistance improves radiologists’ agreement with a text-based reference standard in inferring the modified American Heart Association carotid plaque classification from free-text MRI reports, and whether a lightweight model can perform well under criteria-guided prompting.\n\nMaterials and methods: This retrospective study included 433 patients from three institutions. In a report-based reader study, four radiologists classified MRI reports with and without large language model assistance. In standalone evaluation, a rule-based baseline and 10 models were compared under naive and criteria-guided prompting. The reference standard was expert consensus based on the report text.\n\nResults: Among 433 patients (mean age, 65.9 years ± 13.4; 248 males), AI assistance improved six-class agreement with the text-based reference standard. At the vessel level, junior radiologists improved from 61.75% to 83.12% (Qwen3-8B) and 87.75% (DeepSeek-R1); senior radiologists from 77.00% to 87.50% and 92.25%, respectively (all Holm-corrected p < 0.001). Patient-level agreement increased from 41.0% to 78.8% (junior) and from 59.8% to 87.8% (senior) with DeepSeek-R1. Agreement increased (quadratic-weighted κ : 0.231 without AI vs 0.775 with DeepSeek-R1). In standalone evaluation, criteria-guided prompting improved Qwen3-8B agreement from 38.91% to 81.52% (95% CI: 78.87–84.06%), remaining 5.89 percentage points below DeepSeek-R1 (87.41%; 95% CI: 85.10–89.61%).\n\nConclusion: In this report-based classification setting, large language model assistance improved radiologists’ agreement with the text-based reference standard, with larger gains in junior radiologists. When prompts explicitly encoded AHA criteria, an 8B local candidate model performed well, supporting its potential use as a standardization aid for text-based workflows.\n\nKey Points: Question Report-based modified AHA classification of carotid plaques is experience-dependent and difficult to standardize, as mapping multi-sequence imaging findings to classification conclusions imposes substantial cognitive load.\n\nFindings Large language model assistance improved agreement with a text-based reference standard and raised inter-reader consistency (weighted κ 0.231–0.775), narrowing the junior–senior gap.\n\nCritical relevance statement Embedding explicit AHA criteria in the prompt let an 8B model approach 671B-model agreement (38.91–81.52%), supporting standardized text-based workflows without fine-tuning.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 13,
  "authors": [
    {
      "name": "Mengfei Wang"
    },
    {
      "name": "Yixiao Tang"
    },
    {
      "name": "Yulu Yang"
    },
    {
      "name": "Yifan Tu"
    },
    {
      "name": "Zhongzheng Cao"
    },
    {
      "name": "Runjianya Ling"
    },
    {
      "name": "Kaiyue Sun"
    },
    {
      "name": "Jian Ma"
    },
    {
      "name": "Zhicheng Zhang"
    },
    {
      "name": "Ruipeng Zhang"
    },
    {
      "name": "Xiaoer Wei"
    },
    {
      "name": "Dan Wang"
    },
    {
      "name": "Yuehua Li",
      "orcid": "0000-0003-2417-0867"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/eja5d6028pk0e.bib",
  "cited_by": 0,
  "doi": "10.1186/s13244-026-02421-2",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13675435/?tool=EBI",
  "id": "eja5d6028pk0e",
  "issns": [
    "1869-4101"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13675435",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2740|Cerebrovascular and Carotid Artery Diseases"
    ]
  ],
  "openalex": "W7222640187",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13675435/pdf/?tool=EBI",
  "pmcid": "PMC13675435",
  "pmid": null,
  "published": "2026-10-16",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/eja5d6028pk0e.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:25Z",
      "native_id": "PMC:PMC13675435",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13675435"
    },
    {
      "first_seen": "2026-10-30T12:20:33Z",
      "native_id": "10.1186/s13244-026-02421-2",
      "source": "crossref",
      "url": "https://link.springer.com/article/10.1186/s13244-026-02421-2"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "issn:1869-4101",
      "subfield": "imaging"
    }
  ],
  "title": "Large language model assistance for report-based carotid plaque AHA classification: a multi-reader study",
  "title_text": "Large language model assistance for report-based carotid plaque AHA classification: a multi-reader study",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:33Z",
  "url": "https://research.draconitic.com/paper/eja5d6028pk0e",
  "venue": "Insights into imaging",
  "versions": []
}