Alves José, Azevedo Rita, Marques Ana, Encarnação Rúben, Alves Paulo
Center for Interdisciplinary Research in Health, Faculty of Health Sciences and Nursing, Universidade Católica Portuguesa, 4169-005 Porto, Portugal.
Intensive Care Unit, Braga Local Healthcare Unit, 4710-243 Braga, Portugal.
Nurs Rep. 2025 Apr 9;15(4):126. doi: 10.3390/nursrep15040126.
Pressure injuries pose a significant challenge in healthcare, adversely impacting individuals' quality of life and healthcare systems, particularly in intensive care units. The effective identification of at-risk individuals is crucial, but traditional scales have limitations, prompting the development of new tools. Artificial intelligence offers a promising approach to identifying and preventing pressure injuries in critical care settings. This review aimed to assess the extent of the literature regarding the use of artificial intelligence technologies in the prediction of pressure injuries in critically ill patients in intensive care units to identify gaps in current knowledge and direct future research. The review followed the Joanna Briggs Institute's methodology for scoping reviews, and the study protocol was prospectively registered on the Open Science Framework platform. This review included 14 studies, primarily highlighting the use of machine learning models trained on electronic health records data for predicting pressure injuries. Between 6 and 86 variables were used to train these models. Only two studies reported the clinical deployment of these models, reporting results such as reduced nursing workload, decreased prevalence of hospital-acquired pressure injuries, and decreased intensive care unit length of stay. Artificial intelligence technologies present themselves as a dynamic and innovative approach, with the ability to identify risk factors and predict pressure injuries effectively and promptly. This review synthesizes information about the use of these technologies and guides future directions and motivations.
压力性损伤给医疗保健带来了重大挑战，对个人生活质量和医疗系统产生不利影响，在重症监护病房尤其如此。有效识别高危个体至关重要，但传统量表存在局限性，这促使了新工具的开发。人工智能为在重症监护环境中识别和预防压力性损伤提供了一种很有前景的方法。本综述旨在评估关于在重症监护病房中使用人工智能技术预测重症患者压力性损伤的文献范围，以找出当前知识的差距并指导未来研究。该综述遵循乔安娜·布里格斯研究所的范围综述方法，研究方案已在开放科学框架平台上进行前瞻性注册。本综述纳入了14项研究，主要突出了使用基于电子健康记录数据训练的机器学习模型来预测压力性损伤。用于训练这些模型的变量有6至86个。只有两项研究报告了这些模型的临床应用情况，报告的结果包括护理工作量减少、医院获得性压力性损伤患病率降低以及重症监护病房住院时间缩短。人工智能技术展现出一种动态且创新的方法，有能力有效且迅速地识别风险因素并预测压力性损伤。本综述综合了有关这些技术应用的信息，并指导未来的方向和动机。
