Predição de lesões por pressão através de inteligência artificial em unidades de cuidados intensivos: protocolo de scoping review

Introduction: Pressure injuries are common adverse events in intensive care units, impacting individuals’ quality of life and increasing healthcare costs. Traditional risk assessment scales have significant limitations in the context of critically ill patients. Artificial intelligence has emerged as a promising approach for early risk identification, offering greater sensitivity and the ability to integrate complex clinical data. Objective: To identify and map the available scientific evidence on the use of artificial intelligence for predicting pressure injuries in critically ill adult patients admitted to intensive care units. Methods: A scoping review will be conducted according to the Joanna Briggs Institute methodology and the PRISMA-ScR checklist. The search will include scientific databases and grey literature sources, with no restrictions on language or publication date. Studies addressing the use of artificial intelligence to predict pressure injuries in intensive care settings will be included. Results: Data will be presented descriptively and narratively, using summary tables to highlight types of artificial intelligence, predictive variables, model performance, and clinical implications. Conclusions: This review will systematize current knowledge, identify research gaps, and support the integration of artificial intelligence-based solutions in nursing practice within intensive care contexts.