Post by Dilek Yılmaz Akyaz

I’m happy to share that our article has been published in Nurse Education in Practice: “Secure and accessible AI in nursing education: A modular agentic chatbot framework comparing ChatGPT-4o with an open-source LLM for chronic wound care” In this study, we developed and evaluated a modular, RAG-based agentic AI chatbot framework for chronic wound care education in nursing and compared an open-source configuration with a commercial model. Our findings showed that while the commercial model performed slightly better overall, the open-source on-premises AI agent demonstrated near-comparable performance, with important advantages in cost, security, local control, and institutional autonomy. This work highlights that accessible, guideline-aligned, and secure AI systems can support nursing education, especially in resource-constrained settings, and may help expand equitable access to high-quality learning tools in chronic wound care. I would like to sincerely thank my advisor, Tuba Şengül , for her guidance and support throughout this work. I am also grateful to my co-authors for this valuable interdisciplinary collaboration: Necip Gürler, Ph.D. , Husnu Samet Bulbul , Özgür Güler, PhD , Asim Evren Yantac , Emir Bedirhan Aydın , and Holly Kirkland-Walsh . I feel very grateful to be part of this collaboration bridging nursing, engineering, and wound care innovation. #NursingEducation #ArtificialIntelligence #Chatbot #RAG #OpenSourceAI #WoundCare #ChronicWoundCare #NurseEducationInPractice #DigitalHealth #NursingResearch