Previously submitted to: JMIR Medical Informatics (no longer under consideration since Oct 05, 2026)
Date Submitted: Oct 5, 2026
Open Peer Review Period: Oct 5, 2026 - Oct 5, 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 Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).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Warning: This is an author submission that is not peer-reviewed or edited.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.
Challenges of Using Generative AI for Charcot Neuroarthropathy Patient Education: An Evaluation of Content Quality, Readability, and Actionability
ABSTRACT
Background:
Charcot neuroarthropathy (CN) is a destructive complication of diabetic peripheral neuropathy requiring clear patient education. Large language models (LLMs) are increasingly consulted, yet their CN material remains unevaluated.
Objective:
To compare the content quality, readability, and actionability of CN patient-education responses generated by five widely accessible LLMs.
Methods:
Twenty standardized patient questions spanning five CN domains were posed in English to GPT-5.6, Gemini 3.6 Flash, DeepSeek-V3.2, Qwen 3.7, and Doubao 2.1 through their official interfaces in August 2026. Each of the 100 responses was scored independently by two orthopedic surgeons (Cohen's κ = 0.92) for content quality (DISCERN, EQIP, GQS, JAMA), readability (ARI, CLI, FKGL, FRES, SMOG, GFOG), and actionability (PEMAT-P). Medians were compared using the Kruskal-Wallis test.
Results:
Gemini 3.6 Flash had the highest DISCERN median (54.5/80), whereas Qwen 3.7 had the highest EQIP median (70.6%). Doubao 2.1 was weakest overall (GQS 3/5; lowest PEMAT-P), and Gemini 3.6 Flash and Doubao 2.1 produced the least readable text (FKGL 13.76 and 10.84) versus Qwen 3.7 and DeepSeek-V3.2 (FRES 62.0 and 60.5). Differences were significant for all quality and readability measures (P < .001) and for JAMA (P = .021), where every model scored a median of 0/4.
Conclusions:
LLMs offer a promising foundation for CN patient education, generating largely understandable responses of moderate quality. Limitations were consistent: poor transparency, reading levels exceeding recommended thresholds, and partial actionability. Because no single model was best across all dimensions, the appropriate choice depends on the intended use. Clinical Trial: N/A
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.