Poster presented June 4, 2026, at the Nursing Knowledge Big Data Science Conference held in Minneapolis.
Learning Objectives:
- Compare the performance of a naïve ChatGPT GenAI model and a domain-trained GenAI chatbot in generating clinically valid, accurate, and useful explanations.
- Evaluate the accuracy of generative AI responses of NCLEX-style Medical-Surgical nursing content
- Identify discrepancies in accuracy and clinical relevance between naïve and domain-trained GenAI models
Background: The integration of generative AI models into nursing education requires validation of their ability to provide accurate and educationally appropriate responses. This study examined the comparative performance of two Generative AI models: a naïve ChatGPT (model 4o) and a trained chatbot (OpenAI) tailored to Jacksonville University Medical-Surgical nursing lecture materials. Questions were designed to reflect common NCLEX question formats and renal concepts critical for undergraduate nursing comprehension.
Full abstract available in the conference proceedings, available online and as a downloadable PDF. See link below.