Adaptive AI Case Study: Enhancing Nursing Education with ChatGPT
An adaptive AI-driven unfolding case study using ChatGPT provided nursing students with a dynamic, real-time simulation of an ischemic stroke scenario, enhancing critical thinking, clinical decision-making, and bridging the gap between theory and practice.
Presented by:
Judith Caroline Quick, Auburn University
Abstract:
Innovating nursing education, this adaptive AI-driven unfolding case study utilized ChatGPT to simulate a patient experiencing an ischemic stroke. Dividing 112 students into three groups, the study began with ChatGPT providing an EMS report, dynamically generating information from lecture notes. Students engaged in the full nursing process, from assessment to intervention, adapting to evolving patient responses and executing virtual medical orders. ChatGPT graded performance using a pre-established rubric, offering personalized feedback. This method not only reinforced nursing theory but also honed critical thinking by allowing real-time adaptive learning and decision-making in a controlled, yet realistic, clinical scenario.
Keywords:
Adaptive Learning, Nursing Education, Artificial Intelligence
Learning Outcomes:
1. Summarize AI-driven case scenarios that enable nursing students to engage in comprehensive assessments, analysis, action, and evaluation with an adaptive virtual patient, enhancing practical clinical skills.
2. Critique the effectiveness of AI tools, such as ChatGPT, in delivering personalized feedback and grading, focusing on critical thinking, clinical decision-making, and maintaining academic integrity.
3. Adapt best practices for incorporating AI technologies into nursing education curricula, including developing course materials, executing formative and summative assessments, and promoting interactive learning while managing challenges like accuracy, bias, and over-reliance on AI tools.
Adaptive AI Case Study: Enhancing Nursing Education with ChatGPT
Hear it from the author:
Transcript:
Hello, my name is Judith Caroline Quick, and I’m excited to share my poster titled “Adaptive AI Case Study: Enhancing Nursing Education with ChatGPT.”
This project explored how artificial intelligence—specifically ChatGPT—can be integrated into nursing education through an adaptive, unfolding case study. The focus was on simulating the care of a patient experiencing an ischemic stroke. I uploaded lecture materials into ChatGPT, which then generated a dynamic EMS report. Students worked through the full nursing process: assessment, prioritization, intervention, and evaluation, all while ChatGPT acted as the patient and adapted its responses in real time based on student decisions.
At the end of the case, ChatGPT used a faculty-designed rubric to grade the students’ clinical judgment and provide immediate, personalized feedback.
The outcomes were promising—students were highly engaged, faculty workload for simulation setup was reduced, and learners gained real-time experience applying critical thinking in a low-risk, interactive environment.
This method supports curriculum goals and represents a scalable, innovative solution to modernize nursing education. I believe this approach can be expanded across specialties and settings, including interprofessional collaboration.
Thank you for listening, and please reach out if you'd like to learn more about integrating AI into your own teaching.
References
Castonguay, A., Farthing, P., Davies, S., Vogelsang, L., Kleib, M., Risling, T., & Green, N. (2023). Revolutionizing nursing education through Ai integration: A reflection on the disruptive impact of ChatGPT. Nurse Education Today, 129, 105916. https://doi.org/10.1016/j.nedt.2023.105916
Liu, J., Liu, F., Fang, J., & Liu, S. (2023). The application of Chat Generative Pre-trained Transformer in nursing education. Nursing Outlook, 71(6), 102064. https://doi.org/10.1016/j.outlook.2023.102064
Thakur, A., Parikh, D., & Thakur, A. (2023). ChatGPT in nursing education: Is there a role for curriculum development?. Teaching and Learning in Nursing, 18(3), 450-451. https://doi.org/10.1016/j.teln.2023.03.011