Diagnosing actinic keratosis and squamous cell carcinoma with large language models from clinical images

Actinic keratosis (AK) is a common ultraviolet (UV)-inducedprecancerous skin lesion that may progress to squamous cellcarcinoma (SCC), a potentially invasive malignancy [1, 2].Clinically differentiating between AK and SCC is challengingdue to overlapping features [3]. With the rise of accessible mul-timodal large language models (LLMs), patients now have ar-tificial intelligence (AI) tools such as ChatGPT to assess theirskin lesions at home. However, the diagnostic reliability of thesemodels in distinguishing AK from SCC remains unclear. Thisstudy evaluates and compares two advanced LLMs in identify-ing and differentiating between AK and SCC using real-worldclinical images