Emotional analysis of operating room nurses in acute care hospitals in Japan: insights using ChatGPT

Abstract

Aim: This study aimed to explore the emotions of operating room nurses in Japan towards perioperative nursing using generative AI and human analysis, and to identify factors contributing to burnout and turnover. Methods: A single-center cross-sectional study was conducted from February 2023 to February 2024, involving semi-structured interviews with 10 operating room nurses from a national hospital in Japan. Interview transcripts were analyzed using generative AI (ChatGPT-4o) and human researchers for thematic, emotional, and subjectivity analysis. A comparison between AI and human analysis was performed, and data visualization techniques, including keyword co-occurrence networks and cluster analysis, were employed to identify patterns and relationships. Results: Key themes such as patient care, surgical safety, and nursing skills were identified through thematic analysis. Emotional analysis revealed a range of tones, with AI providing an efficient overview and human researchers capturing nuanced emotional insights. High subjectivity scores indicated deeply personal reflections. Keyword co-occurrence networks and cluster analysis highlighted connections between themes and distinct emotional experiences. Conclusions: Combining generative AI with human expertise offered nuanced insights into the emotions of operating room nurses. The findings emphasize the importance of emotional support, effective communication, and safety protocols in improving nurse well-being and job satisfaction. This hybrid approach can help address emotional challenges, reduce burnout, and enhance retention rates. Future research with larger and more diverse samples is needed to validate these findings and explore the broader applications of AI in healthcare.