{
  "abstract": "Reflective writing assessment in medical education is labor-intensive and raises data privacy concerns that preclude cloud-based AI solutions. We conducted a feasibility study using a locally-hosted, open-weight large language model (LLM) deployed on institutional servers to assess medical students' reflective writing. The model evaluated 10 de-identified student narratives using two published rubrics across three independent passes, generating rubric-aligned scores and formative feedback. Scores were consistent across passes and rubrics with no statistically significant differences. Expert faculty rated LLM-generated feedback as meeting most quality criteria (mean 5.48/7). These findings support feasibility of a privacy-preserving, locally-hosted LLM for scalable reflective writing assessment.Supplementary information\n\nThe online version contains supplementary material available at https://doi.org/10.1007/s40670-026-02865-7.",
  "abstract_shown": true,
  "affiliations": [
    "Cleveland Clinic Lerner College of Medicine at Case Western Reserve University, Cleveland, OH USA.",
    "Department of Medical Education, Tufts University School of Medicine, 136 Harrison Ave., Boston, MA USA.",
    "Department of Medicine, Indiana University School of Medicine, Indianapolis, IN USA."
  ],
  "article_type": "brief report",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Rick Rejeleene",
      "orcid": "0000-0003-1012-8289"
    },
    {
      "affs": [
        1
      ],
      "name": "Jessica N Byram",
      "orcid": "0000-0001-7097-8352"
    },
    {
      "affs": [
        2
      ],
      "name": "Richard M Frankel",
      "orcid": "0000-0003-4132-4506"
    },
    {
      "affs": [
        0
      ],
      "name": "J Harry Isaacson",
      "orcid": "0000-0002-6791-7898"
    },
    {
      "affs": [
        0
      ],
      "name": "Neil B Mehta",
      "orcid": "0000-0001-8342-4252"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/7xpbv3egh76tp.bib",
  "cited_by": 1,
  "doi": "10.1007/s40670-026-02865-7",
  "fulltext_url": "https://europepmc.org/articles/PMC13723480",
  "id": "7xpbv3egh76tp",
  "issns": [
    "2156-8650"
  ],
  "landing_url": "https://europepmc.org/article/MED/42968798",
  "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": [
    [
      "heading",
      "Short Communication"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7204941926",
  "pdf_url": "https://europepmc.org/articles/PMC13723480?pdf=render",
  "pmcid": "PMC13723480",
  "pmid": "42968798",
  "published": "2026-09-01",
  "publisher": "Springer",
  "ris": "https://research.draconitic.com/paper/7xpbv3egh76tp.ris",
  "sources": [
    {
      "first_seen": "2026-11-03T15:20:53Z",
      "native_id": "MED:42968798",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42968798"
    },
    {
      "first_seen": "2026-11-04T12:22:06Z",
      "native_id": "PMC13723480",
      "source": "pmc",
      "url": "https://doi.org/10.1007/s40670-026-02865-7"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Feasibility of Privacy-preserving Locally Hosted Language Models for Assessing Medical Student Reflective Writing.",
  "title_text": "Feasibility of Privacy-preserving Locally Hosted Language Models for Assessing Medical Student Reflective Writing.",
  "type": "peer-reviewed",
  "updated_at": "2026-11-05T12:20:17Z",
  "url": "https://research.draconitic.com/paper/7xpbv3egh76tp",
  "venue": "Medical science educator",
  "versions": []
}