Large language models for dermatological image interpretation - a comparative study.

Abstract

Objectives: Interpreting skin findings can be challenging for both laypersons and clinicians. Large language models (LLMs) offer accessible decision support, yet their diagnostic capabilities for dermatological images remain underexplored. This study evaluated the diagnostic performance of LLMs based on image interpretation of common dermatological diseases.

Methods: A total of 500 dermatological images, encompassing four prevalent skin conditions (psoriasis, vitiligo, erysipelas and rosacea), were used to compare seven multimodal LLMs (GPT-4o, GPT-4o mini, Gemini 1.5 Pro, Gemini 1.5 Flash, Claude 3.5 Sonnet, Llama3.2 90B and 11B). A standardized prompt was used to generate one top diagnosis.

Results: The highest overall accuracy was achieved by GPT-4o (67.8 %), followed by GPT-4o mini (63.8 %) and Llama3.2 11B (61.4 %). Accuracy varied considerably across conditions, with psoriasis with the highest mean LLM accuracy of 59.2 % and erysipelas demonstrating the lowest accuracy (33.4 %). 11.0 % of all images were misdiagnosed by all LLMs, whereas 11.6 % were correctly diagnosed by all models. Correct diagnoses by all LLMs were linked to clear, disease-specific features, such as sharply demarcated erythematous plaques in psoriasis. Llama3.2 90B was the only LLM to decline diagnosing images, particularly those involving intimate areas of the body.

Conclusions: LLM performance varied significantly, emphasizing the need for cautious usage. Notably, a free, locally hostable model correctly identified the top diagnosis for approximately two-thirds of all images, demonstrating the potential for safer, locally deployed LLMs. Advancements in model accuracy and the integration of clinical metadata could further enhance accessible and reliable clinical decision support systems.