{
  "abstract": "Large language models (LLMs) have the potential to make clinical notes more understandable to patients, but tools must be tested with patients pre-deployment. We developed a patient-facing tool that uses an LLM (GPT-4-031) to generate “augmentations” to notes: simplified note text, defined medical terminology, frequently asked questions, extracted key information, and to-do items. We evaluated the tool with 200 healthy female participants and 8 notes. Compared to control, participants with access to augmentations had greater self-reported confidence (2.83 ± 0.05 augmentations, 2.18 ± 0.07 control, p<0.001) and scored higher on comprehension questions (0.63 ± 0.02 augmentations, 0.54 ± 0.04 control, p<0.001). We conducted interviews with 7 participants with a history of breast cancer and their own notes who described ease of use and perceived improvements in note understanding, but also reported concerns around LLMs. Three clinicians conducted an error analysis and found most errors to be minor and related to assumed context.",
  "abstract_shown": true,
  "affiliations": [
    "Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, 02139, MA, USA",
    "University of Michigan, 2260 Hayward St, Ann Arbor, 48109, MI, USA",
    "Division of Hematology and Oncology, Department of Medicine, University of Washington, 825 Eastlake Avenue East, Seattle, 98109, WA, USA",
    "Microsoft Research, 14820 NE 36th St, Redmond, 98052, WA, USA",
    "Massachusetts General Hospital, 55 Fruit St, Boston, 02114, MA, USA",
    "School of Medicine, Stanford University, 291 Campus Drive, Stanford, 94305, CA, USA",
    "Department of Oncology, Mayo Clinic, 5777 E. Mayo Blvd., Phoenix, 85054, AZ, USA",
    "Duke University, 2424 Erwin Rd, Durham, 27708, NC, USA"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 13,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Niklas Mannhardt"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Elizabeth Bondi",
      "orcid": "0000-0002-8459-8403"
    },
    {
      "affs": [
        2
      ],
      "name": "Barbara D. Lam"
    },
    {
      "affs": [
        0,
        3
      ],
      "name": "Hussein Mozannar",
      "orcid": "0009-0001-9660-9878"
    },
    {
      "affs": [
        4,
        5
      ],
      "name": "Chloe P. O’Connell",
      "orcid": "0000-0002-0470-2339"
    },
    {
      "affs": [
        0
      ],
      "name": "Mercy Asiedu",
      "orcid": "0000-0002-0230-5022"
    },
    {
      "affs": [
        5
      ],
      "name": "Alejandro Buendia",
      "orcid": "0009-0001-6562-9876"
    },
    {
      "affs": [
        0
      ],
      "name": "Tatiana Urman"
    },
    {
      "affs": [
        6
      ],
      "name": "Irbaz Bin Riaz",
      "orcid": "0000-0003-4249-0311"
    },
    {
      "affs": [
        0
      ],
      "name": "Catherine Ricciardi"
    },
    {
      "affs": [
        7,
        0
      ],
      "name": "Monica Agrawal",
      "orcid": "0009-0003-5116-2819"
    },
    {
      "affs": [
        0
      ],
      "name": "Marzyeh Ghassemi",
      "orcid": "0000-0001-6349-7251"
    },
    {
      "affs": [
        0
      ],
      "name": "David Alexander Sontag",
      "orcid": "0000-0002-5034-7796"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2kmf9b4ryv64s.bib",
  "cited_by": 15,
  "doi": "10.1038/s41598-026-59948-z",
  "fulltext_url": null,
  "id": "2kmf9b4ryv64s",
  "issns": [
    "2045-2322"
  ],
  "landing_url": "https://www.nature.com/articles/s41598-026-59948-z",
  "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": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W4391045928",
  "pdf_url": "https://www.nature.com/articles/s41598-026-59948-z.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-05",
  "publisher": "Springer Science and Business Media LLC",
  "ris": "https://research.draconitic.com/paper/2kmf9b4ryv64s.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T12:20:13Z",
      "native_id": "10.1038/s41598-026-59948-z",
      "source": "crossref",
      "url": "https://www.nature.com/articles/s41598-026-59948-z"
    },
    {
      "first_seen": "2026-11-07T13:20:59Z",
      "native_id": "W4391045928",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41598-026-59948-z"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "A mixed-methods evaluation of a language model-powered breast cancer note augmentation tool for patients",
  "title_text": "A mixed-methods evaluation of a language model-powered breast cancer note augmentation tool for patients",
  "type": "peer-reviewed",
  "updated_at": "2026-11-09T13:21:16Z",
  "url": "https://research.draconitic.com/paper/2kmf9b4ryv64s",
  "venue": "Scientific Reports",
  "versions": []
}