{
  "abstract": "Objective: To compare ChatGPT-4o, ChatGPT-5, and DeepSeek-R1 in assigning main Coronary Artery Disease Reporting and Data System (CAD-RADS) categories from findings-only coronary computed tomography angiography (CCTA) reports and to characterize management-relevant classification errors.\n\nMethods: This retrospective diagnostic-accuracy study included 2,100 category-balanced findings-only CCTA reports (300 per CAD-RADS category). Two experienced CCTA radiologists graded the English-translated reports; 12 disagreements were resolved by a third. ChatGPT-4o was evaluated in standard mode, ChatGPT-5 in Thinking mode, and DeepSeek-R1 in Deep Thinking mode; model generation and inference mode therefore varied together. Exact-match accuracy with 95% Wilson confidence intervals (CIs), paired comparisons, and unweighted Gwet AC1 with 95% CIs were calculated. Management-relevant transitions and digital subtraction angiography (DSA) findings among high-risk downgrades were analyzed.\n\nResults: DeepSeek-R1 had an exact-match accuracy of 82.57% (95% CI, 80.89–84.13) and AC1 of 0.797 (95% CI, 0.778–0.816). ChatGPT-5 had an accuracy of 80.19% (95% CI, 78.43–81.84) and AC1 of 0.769 (95% CI, 0.749–0.789), whereas ChatGPT-4o had an accuracy of 53.62% (95% CI, 51.48–55.74) and AC1 of 0.460 (95% CI, 0.435–0.485). Cochran's Q test was significant (Q = 657.87; df = 2; P < 0.001); after Holm correction, DeepSeek-R1 also outperformed ChatGPT-5 in the paired comparison ( P = 0.026), and both outperformed ChatGPT-4o (both P < 0.001). ChatGPT-4o downgraded 127/900 (14.11%) reference high-risk reports to CAD-RADS 3 or lower. Of these 127 cases, 65 underwent DSA within three months; DSA supported the original high-risk assessment in 56/65 (86.15%). The corresponding high-risk downgrade proportions were 37/900 (4.11%) for ChatGPT-5 and 23/900 (2.56%) for DeepSeek-R1.\n\nConclusion: The DeepSeek-R1 Deep Thinking and ChatGPT-5 Thinking configurations achieved higher accuracy than ChatGPT-4o in standard mode. Because model generation and inference mode varied together, the results do not isolate a model-family effect. LLMs merit further evaluation for secondary structuring when no documented CAD-RADS category is available, but should not overwrite a radiologist-assigned category or independently determine management.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Radiology, The Eighth Affiliated Hospital, Southern Medical University , , ,",
    "Department of Clinical Laboratory, Lecong Hospital of Shunde , , ,",
    "Department of Ultrasound, The Eighth Affiliated Hospital, Southern Medical University , , ,"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Haorong Rong"
    },
    {
      "affs": [
        1
      ],
      "name": "Xiyi Huang"
    },
    {
      "affs": [
        0
      ],
      "name": "Xinjie Chen"
    },
    {
      "affs": [
        2
      ],
      "name": "Lizhu Ouyang"
    },
    {
      "affs": [
        0
      ],
      "name": "Yuelu Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Xin Lin"
    },
    {
      "affs": [
        0
      ],
      "name": "Jialing Pan"
    },
    {
      "affs": [
        0
      ],
      "name": "Yunjing Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Fan Xie"
    },
    {
      "affs": [
        0
      ],
      "name": "Fusheng Ouyang"
    },
    {
      "affs": [
        0
      ],
      "name": "Qiugen Hu"
    },
    {
      "affs": [
        0
      ],
      "name": "Baoliang Guo"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/3rfv5v7g9ac24.bib",
  "cited_by": 0,
  "doi": "10.3389/fcvm.2026.1909068",
  "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13690529/?tool=EBI",
  "id": "3rfv5v7g9ac24",
  "issns": [
    "2297-055X"
  ],
  "landing_url": "https://europepmc.org/article/PMC/PMC13690529",
  "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",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7221147015",
  "pdf_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13690529/pdf/?tool=EBI",
  "pmcid": "PMC13690529",
  "pmid": null,
  "published": "2026-10-09",
  "publisher": "Frontiers Media SA",
  "ris": "https://research.draconitic.com/paper/3rfv5v7g9ac24.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:59Z",
      "native_id": "PMC:PMC13690529",
      "source": "europepmc",
      "url": "https://europepmc.org/article/PMC/PMC13690529"
    },
    {
      "first_seen": "2026-10-30T12:20:10Z",
      "native_id": "10.3389/fcvm.2026.1909068",
      "source": "crossref",
      "url": "https://www.frontiersin.org/articles/10.3389/fcvm.2026.1909068/full"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Large language model-assisted CAD-RADS classification: structured report extraction, accuracy, and clinical decision-making risk of ChatGPT-4o/5 and DeepSeek-R1",
  "title_text": "Large language model-assisted CAD-RADS classification: structured report extraction, accuracy, and clinical decision-making risk of ChatGPT-4o/5 and DeepSeek-R1",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:20:10Z",
  "url": "https://research.draconitic.com/paper/3rfv5v7g9ac24",
  "venue": "Frontiers in cardiovascular medicine",
  "versions": []
}