{
  "abstract": "Invasive coronary angiography is the reference standard for diagnosing coronary artery disease, yet assessment is subjective, and existing artificial-intelligence tools typically assess stenosis in individual frames or videos and do not integrate the full multiview angiographic study. Here we show that DeepCORO-CLIP, trained on 203,808 angiographic videos and reports from 28,117 patients, interprets whole multiple-video angiograms at once. It detects obstructive stenoses (≥70%), with an area under the receiver operating characteristic curve (AUROC) of 0.89 internally and externally, and identifies chronic total occlusion (AUROC = 0.90 to 0.95), intra-coronary thrombus and calcification (AUROC = 0.90 to 0.91). It also predicts 1-year cardiovascular events (AUROC = 0.79, 95% CI of 0.74 to 0.84, versus 0.65 for a model derived using clinical variables) and left ventricular ejection fraction (mean absolute error 7.3% versus 8.8% for a previous model), both achieved using coronary angiography alone. In a blinded review of 365 evaluations across 288 angiograms, its reports were clinically usable in 76% of evaluations versus 88% for cardiologists, with comparable false positives (17% versus 14%, P = 0.38); residual missed stenoses reflected an adjustable threshold rather than an absent signal.",
  "abstract_shown": true,
  "affiliations": [
    "Division of Cardiology, Department of Medicine, Montreal Heart Institute, Université de Montréal, Montreal, Quebec Canada",
    "HeartWise.ai, Montreal, Quebec Canada",
    "Faculty of Engineering, McGill University, Montreal, Quebec Canada",
    "Department of Medicine, Université de Montréal, Montreal, Quebec Canada",
    "Division of Cardiology, Department of Medicine, University of California, San Francisco, CA USA",
    "Cardiovascular Research Institute, University of California, San Francisco, CA USA",
    "Bakar Computational Health Sciences Institute, University of California, San Francisco, CA USA",
    "Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA USA",
    "Department of Bioengineering, University of California Los Angeles, Los Angeles, CA USA",
    "Department of Medicine, Kaiser Permanente, San Francisco, CA USA"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 12,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Sarra Harrabi"
    },
    {
      "affs": [
        2
      ],
      "name": "Yichen Wu",
      "orcid": "0009-0000-2771-1505"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Omar Majwal",
      "orcid": "0009-0007-6370-5816"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Gabriel Asslo"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "George Azar",
      "orcid": "0009-0006-5663-6413"
    },
    {
      "affs": [
        4,
        5,
        6
      ],
      "name": "Geoffrey H. Tison",
      "orcid": "0000-0002-0310-3326"
    },
    {
      "affs": [
        4,
        5,
        6
      ],
      "name": "Minhaj Ansari"
    },
    {
      "affs": [
        7,
        8
      ],
      "name": "Milos Vukadinovic"
    },
    {
      "affs": [
        7,
        9
      ],
      "name": "David Ouyang"
    },
    {
      "affs": [
        5,
        6,
        7
      ],
      "name": "Joshua P. Barrios",
      "orcid": "0000-0003-1618-6244"
    },
    {
      "affs": [
        0,
        2
      ],
      "name": "Jacques Delfrate",
      "orcid": "0009-0001-0466-1354"
    },
    {
      "affs": [
        0,
        1,
        3
      ],
      "name": "Robert Avram",
      "orcid": "0000-0002-8490-0270"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/652804q7gtnnw.bib",
  "cited_by": 1,
  "doi": "10.1038/s44161-026-00890-8",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13759332/",
  "id": "652804q7gtnnw",
  "issns": [
    "2731-0590"
  ],
  "landing_url": "https://doi.org/10.1038/s44161-026-00890-8",
  "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",
      "Article"
    ],
    [
      "openalex",
      "2741|Cardiac Imaging and Diagnostics"
    ]
  ],
  "openalex": "W7221696069",
  "pdf_url": "https://www.nature.com/articles/s44161-026-00890-8.pdf",
  "pmcid": "PMC13759332",
  "pmid": "42869976",
  "published": "2026-10-13",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/652804q7gtnnw.ris",
  "sources": [
    {
      "first_seen": "2026-11-16T12:23:59Z",
      "native_id": "PMC13759332",
      "source": "pmc",
      "url": "https://doi.org/10.1038/s44161-026-00890-8"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2741|Cardiac Imaging and Diagnostics",
      "subfield": "imaging"
    }
  ],
  "title": "A multiview video–text model detects obstructive coronary stenosis and predicts 1-year cardiovascular events from angiography",
  "title_text": "A multiview video–text model detects obstructive coronary stenosis and predicts 1-year cardiovascular events from angiography",
  "type": "peer-reviewed",
  "updated_at": "2026-11-16T12:23:59Z",
  "url": "https://research.draconitic.com/paper/652804q7gtnnw",
  "venue": "Nature Cardiovascular Research",
  "versions": []
}