Exploring nurses' acceptability and readiness for patient-centered artificial intelligence systems in pressure injury prevention

Abstract

This study explores nurses' acceptability and readiness to integrate patient-centered artificial intelligence (AI) technologies for pressure injury (PI) prevention, aiming to inform the design of clinically applicable technologies.METHODS:This qualitative descriptive study gathered insights from 202 international nurses in 2 countries through focus group discussions and written responses. Thematic analysis was conducted using MAXQDA.RESULTS:Three main concepts were identified. Under the use of manual tools in risk assessment, the theme was clinical challenges of the Braden Scale, with subthemes of accuracy and reliability, limitations in specific patient populations, and patient nonmodifiable related risk stratification. Within integration of AI-based technologies, themes included expectations from AI-based systems, with subthemes of advanced risk stratification prediction and real-time data, and concerns about AI integration in the system, with subthemes of acceptability level, education and awareness, data accuracy and reliability, and ethical issues and patient safety. For patient-centered monitoring systems, themes included development of automated documentation with subthemes of reducing workload, time management, integration of early warning systems with subthemes of automated monitoring, early intervention, and AI-supported decision support systems with subthemes of personalized interventions and proactive intervention.CONCLUSIONS:Current nurse-led risk assessment systems require improvement for specific patient groups, affecting safety and care quality. Artificial intelligence-based systems can provide more accurate risk predictions and personalized interventions, enhancing decision-making and clinical outcomes. Although nurses are ready for AI adoption, further education is needed for full integration to optimize patient care.