| Autor: |
Deliyannis, Eduardo Panaiotis, Paul, Navreet, Patel, Priya U, Papanikolaou, Marieta |
| Předmět: |
|
| Zdroj: |
Clinical & Experimental Dermatology; Jul2024, Vol. 49 Issue 7, p743-746, 4p |
| Abstrakt: |
This article presents a comparative analysis of three large language models (LLMs) in answering patient questions about melanoma. The LLMs evaluated were ChatGPT 3.5, ChatGPT 4.0, and Google Bard. Dermatologists scored the responses generated by the LLMs based on accuracy, reproducibility, readability, and comprehensiveness. The results showed that ChatGPT 3.5 performed the best, highlighting the limitations of relying solely on LLMs for medical information. Larger studies are needed to fully understand the impact of LLMs on the dissemination of medical information. [Extracted from the article] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
