{
  "abstract": "Background: Each year, 350,000 people in the United States experience out-of-hospital cardiac arrest, and 90% do not survive. Early cardiopulmonary resuscitation (CPR) can double or triple survival rates.\n\nProject Rationale: Bystander CPR is performed correctly in fewer than 40% of cases, with major challenges persisting: lack of widespread training, decision paralysis, and recall bias during an emergency.\n\nProject Summary: Universal CPR Assistance and Response Engine (U-CARE) is a low-cost smartphone-based system that serves as a universal CPR guide to address these challenges. A large language model–powered verbal guidance system provides objective next-best steps multilingually, coupled with a computer vision model that continuously assesses CPR technique. U-CARE was evaluated using holistic large language model evaluation and computer vision metrics, and outperformed out-of-the-box frontier models on relevance and safety in human evaluation, demonstrating its viability for real-time feedback.\n\nTake-Home Message: U-CARE demonstrates the feasibility of a smartphone-based multimodal CPR feedback and response agent for emergency and training guidance.",
  "abstract_shown": true,
  "affiliations": [
    "Stanford University Online High School, Redwood City, California, USA",
    "Research Fellow, GSE, Stanford University, Stanford, California, USA",
    "Center for Precision Medicine, University of California Davis Health, Davis, California, USA",
    "Department of Anesthesiology, Cleveland Clinic, Cleveland, Ohio, USA"
  ],
  "article_type": "case report",
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Aarit Atreja"
    },
    {
      "affs": [
        1
      ],
      "name": "Utkarsh Contractor"
    },
    {
      "affs": [
        2
      ],
      "name": "Dharan Jaisankar"
    },
    {
      "affs": [
        3
      ],
      "name": "Piyush Mathur"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/d387g68y7131b.bib",
  "cited_by": 0,
  "doi": "10.1016/j.jaccas.2026.110026",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13728405/",
  "id": "d387g68y7131b",
  "issns": [
    "2666-0849"
  ],
  "landing_url": "https://doi.org/10.1016/j.jaccas.2026.110026",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Critical Care and Resuscitation"
    ],
    [
      "heading",
      "Quality Improvement Projects"
    ],
    [
      "openalex",
      "2711|Cardiac Arrest and Resuscitation"
    ]
  ],
  "openalex": "W7213436138",
  "pdf_url": null,
  "pmcid": "PMC13728405",
  "pmid": "42752015",
  "published": "2026-09-16",
  "publisher": "Elsevier",
  "ris": "https://research.draconitic.com/paper/d387g68y7131b.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T12:21:24Z",
      "native_id": "PMC13728405",
      "source": "pmc",
      "url": "https://doi.org/10.1016/j.jaccas.2026.110026"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "journal-openalex:2705|Cardiac Valve Diseases and Treatments",
      "subfield": "cardiovascular"
    }
  ],
  "title": "Development and Evaluation of Multimodal Universal CPR AI Assistance and Response Engine (U-CARE)",
  "title_text": "Development and Evaluation of Multimodal Universal CPR AI Assistance and Response Engine (U-CARE)",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T12:21:24Z",
  "url": "https://research.draconitic.com/paper/d387g68y7131b",
  "venue": "JACC Case Reports",
  "versions": []
}