AI-Supported Gamified Training for Sharps Injury Prevention in Nurses

Overview

This study aims to evaluate the effect of a Health Belief Model (HBM)-based, artificial intelligence (AI)-supported gamified training program on nurses' knowledge and attitudes toward the prevention of sharps injuries. Sharps injuries remain a significant occupational risk for healthcare workers, particularly nurses, despite existing standard precautions. The study will be conducted in two phases. In the first phase, the validity and reliability of the Sharps Injury Prediction Scale will be tested in a nurse population. In the second phase, a quasi-experimental pretest-posttest control group design will be used to assess the effectiveness of the intervention. The study will be carried out in two hospitals from the same healthcare group located in different cities to prevent interaction between groups. A total of 36 nurses will be included, with 18 participants in the intervention group and 18 in the control group. The intervention group will receive a structured, HBM-based training program consisting of seven sessions incorporating AI-supported content, gamified scenarios, interactive materials, and feedback mechanisms to enhance engagement and promote behavior change. The control group will receive routine institutional training on sharps injury prevention. Data will be collected at baseline, immediately after the intervention, and two months later. Outcome measures include nurses' knowledge, attitudes toward safe sharps use, and sharps injury risk perception. It is expected that the AI-supported gamified training program will significantly improve knowledge, attitudes, and risk awareness compared to routine training. The findings may support the integration of innovative, theory-based educational interventions into institutional training programs to enhance occupational safety.

Sharps injuries are among the most common occupational hazards for healthcare workers, particularly nurses, due to their frequent exposure to invasive procedures and contact with blood and body fluids. These injuries are associated with the risk of transmission of serious infections such as hepatitis B, hepatitis C, and HIV. Despite the implementation of standard precautions and institutional training programs, the incidence of sharps injuries remains a significant concern, highlighting the need for more effective and behavior-focused educational interventions. Traditional training methods are often limited in their ability to promote sustained behavioral change. In this context, theory-based and technology-supported approaches may provide more effective solutions. The Health Belief Model (HBM) is widely used to explain and predict health-related behaviors by focusing on individuals' perceptions of risk, benefits, barriers, and self-efficacy. Integrating HBM into educational interventions may enhance the effectiveness of training programs aimed at improving safe practices. In addition, recent advances in artificial intelligence (AI) and gamification have introduced innovative opportunities in health education. AI-supported systems can provide personalized learning experiences, while gamification techniques, such as interactive scenarios, feedback, and rewards, can increase motivation, engagement, and knowledge retention. These approaches may be particularly beneficial in nursing education, where active participation and behavioral reinforcement are essential. This study will be conducted in two phases. In the first phase, the validity and reliability of the Sharps Injury Prediction Scale will be evaluated in a nurse population. In the second phase, a quasi-experimental pretest-posttest control group design will be used to assess the effectiveness of an HBM-based, AI-supported gamified training program. The study will be carried out in two hospitals within the same healthcare group located in different cities to minimize interaction between groups. A total of 36 nurses will be included. The intervention group will receive a structured training program consisting of seven sessions designed based on HBM constructs, incorporating AI-supported educational materials, gamified learning tools, and interactive components. The control group will receive routine institutional training. Data will be collected at baseline, immediately after the intervention, and two months after the intervention. Outcome measures will include knowledge levels, attitudes toward safe use of sharps, and risk perception related to sharps injuries. The findings of this study are expected to contribute to the development of innovative, theory-based educational strategies and support the integration of AI-supported and gamified training approaches into healthcare institutions to enhance occupational safety among nurses.