Previously submitted to: Journal of Medical Internet Research (no longer under consideration since Jul 01, 2026)
Date Submitted: Oct 7, 2025
Open Peer Review Period: Oct 7, 2025 - Dec 2, 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 Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).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Warning: This is an author submission that is not peer-reviewed or edited.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.
Effect of Prompt Engineering and Retrieval Augmentation on ChatGPT-4 Diagnostic Accuracy for Congenital Ear Deformities: a Paired Clinical Image Study
ABSTRACT
Background:
The generation of clinical diagnoses from image data is a cornerstone of medical image analysis. ChatGPT-4, a large multimodal model capable of processing both text and image inputs (e.g., dermatoscopic, histologic, and radiographic images), has recently attracted considerable interest in medical artificial intelligence.
Objective:
To evaluate ChatGPT 4's enhanced diagnostic accuracy for congenital ear deformities using prompt engineering and retrieval augmentation.
Methods:
We evaluated ChatGPT-4’s ability to identify superficial facial malformations using four categories of congenital ear deformities—microtia, cryptotia, accessory ears, and prominent ears. Diagnostic accuracy was assessed under four conditions: (1) baseline (no prompt engineering), (2) prompt‑enhanced, (3) Retrieval‑Augmented Generation (RAG) without prompts, and (4) RAG with optimized prompts.
Results:
Baseline accuracy rates were 76.0% for microtia, 3.2% for cryptotia, 8.3% for Accessory ears, and 40.0% for prominent ears. Prompt engineering improved accuracy to 100.0%, 80.6%, 16.7%, and 80.0%, respectively. The RAG approach without prompts yielded identical rates (82.0%, 0.0%, 25.0%, and 0.0%). When combined with optimized prompts within the RAG framework, the model achieved 100% accuracy across all four categories.
Conclusions:
Prompt engineering significantly enhances ChatGPT-4’s diagnostic performance on image‑based tasks, and its integration within a RAG framework delivers optimal accuracy. These findings support the potential of multimodal large language models for reliable clinical image interpretation when augmented with retrieval and tailored prompts.
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.