Publications by authors named "Nadia Cw Kamminga"

Article Synopsis
  • This study assessed how well Large Language Models (LLMs) like ChatGPT and Gemini answered melanoma-related patient questions compared to established Dutch patient information resources (PIRs).
  • ChatGPT-3.5 had the highest accuracy, while Gemini excelled in completeness, personalization, and readability; however, the best LLMs still lagged behind PIRs in accuracy overall.
  • Despite LLMs showing promise for personalized responses, the study highlights the need for improvement in their accuracy and reproducibility before they can fully replace traditional PIRs.
View Article and Find Full Text PDF