The use of a ChatGPT‐4‐based chatbot in teledermatology: A retrospective exploratory study

Abstract

BACKGROUND AND OBJECTIVES: Integration of artificial intelligence in healthcare, particularly ChatGPT, is transforming medical diagnostics and may benefit teledermatology. This exploratory study compared image description and differential diagnosis generation by a ChatGPT-4 based chatbot with human teledermatologists. PATIENTS AND METHODS: This retrospective study compared 154 teledermatology consultations (December 2023-February 2024) with ChatGPT-4's performance in image descriptions and diagnoses. Diagnostic concordance was classified as "Top1" (exact match with the teledermatologist's diagnoses), "Top3" (correct diagnosis within one the top three diagnoses), and "Partial" (similar but not identical diagnoses). Image descriptions were rated and compared for quality parameters (location, color, size, morphology, and surrounding area), and accuracy (Yes, No, and Partial). RESULTS: Out of 154 cases, ChatGPT-4 achieved a Top1 diagnostic concordance in 108 (70.8%), Top3 concordance in 137 (87.7%), partial concordance in four (2.6%), and was discordant in 15 (9.7%) cases. The quality of ChatGPT-4's image descriptions significantly surpassed teledermatologists in all five parameters. ChatGPT-4's descriptions were accurate in 130 (84.4%), partially accurate in 22 (14.3%), and inaccurate in two (1.3%) cases. CONCLUSIONS: The preliminary findings of this study indicate that ChatGPT-4 demonstrates potential in generating accurate image descriptions and differential diagnoses. These results highlight the promise of integrating artificial intelligence into asynchronous teledermatology workflows.

Ähnliche Arbeiten