Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Mar 30, 2026)
Date Submitted: Sep 30, 2025
Open Peer Review Period: Oct 1, 2025 - Nov 26, 2025
(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 Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).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Warning: This is an author submission that is not peer-reviewed or edited.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.
Performance of Large Language Models versus Traditional Chinese Doctors in Migraine Diagnosis and Herbal Prescription: Approaching a Turing Point
ABSTRACT
Background:
Although Traditional Chinese Medicine (TCM) is gaining global recognition, the availability of highly trained experts remains limited. The individualized and dynamically complex nature of TCM herbal formulations presents challenges unmatched in Western medicine.
Objective:
This study evaluates whether advanced, publicly accessible large language models (LLMs) can approximate the diagnostic reasoning and herbal prescription practices of experienced TCM doctors, using a standardized migraine case from a published report.
Methods:
Nine LLMs (eight reasoning-enabled “thinking” models and one non-thinking baseline) were prompted through publicly available interfaces using a structured five-task format (Western diagnosis, TCM diagnosis, treatment principle, herbal prescription, and preventive care). No fine-tuning or external knowledge bases were applied. For comparison, diagnoses and prescriptions from three TCM doctors, including the original case author, were generated using the same prompt. Thirty-two expert raters, blinded to response source, independently scored all outputs across five evaluation dimensions.
Results:
Most reasoning-enabled LLMs achieved performance comparable to that of senior TCM physicians, with several models (e.g., GPT-o3, Qwen-3, Gemini-2.5 Pro) receiving significantly higher scores than one or more physicians in specific tasks. By contrast, the non-thinking baseline model (Aya Expense 32B) performed substantially worse.
Conclusions:
Advanced LLMs may have reached a “Turing point” in TCM, rivaling expert performance. While promising for addressing practitioner shortages, these advances highlight the urgent need for careful regulation and oversight.
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.