Effect of Prompt Engineering and Retrieval Augmentation on ChatGPT-4 Diagnostic Accuracy for Congenital Ear Deformities: a Paired Clinical Image Study (Preprint)

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.