{
  "abstract": "Aims: Large language models (LLMs) are increasingly used by the public and healthcare professionals for clinical reasoning. However, they were developed as general-purpose language models rather than dedicated clinical decision-support tools, and their performance in real-world acute heart failure (AHF) management remains insufficiently evaluated. We compared four contemporary AI models with physician decision-making.\n\nMethods and results: This single-centre retrospective observational study incorporated a cross-sectional AI evaluation of consecutive patients treated at Sotiria General Hospital between July and November 2025, excluding acute coronary syndrome. ChatGPT, ChatGPT Plus, DeepSeek, and an ESC guideline-based retrieval-augmented generation (RAG) model independently assessed identical standardized cases. Recommendations were compared with physician decisions on diagnosis, treatment, guideline-directed medical therapy, timing, and prognosis using Cohen’s kappa, McNemar’s test, Cochran’s Q, Wilcoxon signed-rank testing, and multivariable logistic regression. Diagnostic performance differed significantly across systems (Cochran’s Q = 8.477, P = 0.037). In the balanced diagnostic cohort, ChatGPT Plus achieved the highest heart failure (HF) accuracy (accuracy 86.5%, sensitivity 87.0%, and specificity 86.0%), followed by RAG (accuracy 77.5%), ChatGPT (accuracy 77.0%), and DeepSeek (accuracy 69.0%). For HF within the top three differential diagnoses, sensitivity was 90.0–97.0%; specificity was 70.0% for ChatGPT Plus, 68.0% for RAG, 19.0% for DeepSeek, and 15.0% for ChatGPT. Physician agreement was highest for guideline-directed therapies, with greater variability in prognosis and escalation of care. RAG more closely matched physician therapeutic timing but did not consistently outperform general-purpose models.\n\nConclusion: Contemporary AI models show promise in AHF decision support but substantial task-specific variability, supporting use as complements rather than replacements for physician judgement.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "name": "Georgios E Zakynthinos",
      "orcid": "0000-0003-4444-0967"
    },
    {
      "name": "Evangelos Oikonomou",
      "orcid": "0000-0001-8079-0599"
    },
    {
      "name": "Iason- Daniil Zakynthinos",
      "orcid": "0009-0006-1280-4024"
    },
    {
      "name": "George Dimeas",
      "orcid": "0009-0002-1967-3005"
    },
    {
      "name": "Panteleimon Pantelidis",
      "orcid": "0000-0001-5394-832X"
    },
    {
      "name": "Theodore G Papaioannou",
      "orcid": "0000-0002-1552-3168"
    },
    {
      "name": "Gerasimos Siasos",
      "orcid": "0000-0001-7601-8870"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9x52z1w4xstcm.bib",
  "cited_by": 0,
  "doi": "10.1093/ehjdh/ztag169",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13732570/",
  "id": "9x52z1w4xstcm",
  "issns": [
    "2634-3916"
  ],
  "landing_url": "https://doi.org/10.1093/ehjdh/ztag169",
  "language": "en",
  "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",
      "AcademicSubjects/MED00200"
    ],
    [
      "heading",
      "Eurheartj/23"
    ],
    [
      "heading",
      "Eurheartj/24"
    ],
    [
      "heading",
      "Eurheartj/27"
    ],
    [
      "heading",
      "Eurheartj/28"
    ],
    [
      "heading",
      "Original Article"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7223446231",
  "pdf_url": "https://academic.oup.com/ehjdh/article-pdf/7/9/ztag169/72459464/ztag169.pdf",
  "pmcid": "PMC13732570",
  "pmid": "42985448",
  "published": "2026-10-24",
  "publisher": "Oxford University Press",
  "ris": "https://research.draconitic.com/paper/9x52z1w4xstcm.ris",
  "sources": [
    {
      "first_seen": "2026-11-08T12:22:32Z",
      "native_id": "PMC13732570",
      "source": "pmc",
      "url": "https://doi.org/10.1093/ehjdh/ztag169"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Artificial intelligence versus physician decision-making in acute heart failure: a comparative evaluation of four contemporary AI systems",
  "title_text": "Artificial intelligence versus physician decision-making in acute heart failure: a comparative evaluation of four contemporary AI systems",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T12:22:32Z",
  "url": "https://research.draconitic.com/paper/9x52z1w4xstcm",
  "venue": "European Heart Journal. Digital Health",
  "versions": []
}