Previously submitted to: JMIR Medical Informatics (no longer under consideration since Apr 06, 2026)
Date Submitted: Mar 21, 2026
Open Peer Review Period: Apr 6, 2026 - Apr 6, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Large Language Models for Minimum Data Set Documentation Support in Skilled Nursing Facilities: Opportunities, Risks, and a Proposed Implementation Framework
ABSTRACT
Background:
The Minimum Data Set (MDS) is the federally mandated clinical assessment instrument used in all Medicare- and Medicaid-certified skilled nursing facilities (SNFs) in the United States. Comprising more than 600 coded data elements and directly driving Medicare reimbursement under the Patient-Driven Payment Model (PDPM), MDS documentation imposes a considerable administrative burden on nursing staff. Large language models (LLMs) have shown the capacity to reduce documentation time in acute and ambulatory care, yet no peer-reviewed work has examined their application to the structured, regulatory, and SNF-specific demands of MDS documentation.
Objective:
We identify and characterize the literature gap at the intersection of LLMs and MDS documentation, synthesize existing evidence on LLM deployment in clinical documentation, and propose an implementation framework tailored to the regulatory, workforce, and interoperability constraints of SNF environments.
Methods:
We conducted a structured literature search across PubMed, IEEE Xplore, Scopus, and CINAHL using terms combining large language model, LLM, GPT, minimum data set, MDS, skilled nursing, nursing home, and long-term care documentation. We supplemented this with a review of current CMS regulatory updates, HIPAA guidance, and HL7 FHIR R4 interoperability standards.
Results:
Our search identified zero peer-reviewed publications on LLM application to MDS documentation, despite 41 studies confirming LLM utility in general clinical documentation. We present a three-mode implementation framework — Draft Assist, Consistency Checker, and Query Interface — grounded in Retrieval-Augmented Generation (RAG) architecture using the CMS Resident Assessment Instrument Manual as the knowledge base. We further propose a risk taxonomy covering hallucination by MDS section, automation bias, regulatory liability, and data governance.
Conclusions:
LLMs represent a high-potential, under-explored tool for reducing MDS documentation burden in SNFs. The proposed framework provides a translational roadmap for researchers, EHR vendors, and SNF administrators. Future work should prioritize prospective pilot studies using de-identified or synthetic MDS datasets.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.