Key points are not available for this paper at this time.
Aim This scoping review aimed to identify and map clinical decision support tools (both digital and non-digital) used by clinicians for wound management in acute, primary, and community health settings globally, with a focus on the use of artificial intelligence and the barriers and enablers to implementation. Materials and methods Studies published between January 2015, and August 2024 were identified through systematic searches of Scopus, Embase, MEDLINE, and CINAHL, conducted in accordance with Joanna Briggs Institute methodology and reported using the PRISMA-ScR guidelines. Eligible studies included quantitative, qualitative, and mixed-methods research examining non-digital and AI-supported clinical decision support tools for wound management across healthcare settings. Results Seventeen studies were included, two evaluating AI-supported clinical decision support tools (CDSTs). Most CDSTs supported structured wound assessment and treatment planning, though evidence of clinical effectiveness was limited, with only one tool fully validated. Adoption by nurses was influenced by experience, trust, training, and workflow integration, with senior nurses less likely to rely on CDSTs. AI-enabled tools, including Tissue Analytics™ and a convolutional neural network–based model, improved assessment consistency, documentation, and workflow efficiency. Key barriers included concerns about trust, clinical autonomy, and usability. Conclusions Both traditional and AI-supported CDSTs are used for chronic wound management across acute, primary, and community care, but evidence of effectiveness and validation remains limited. The absence of experimental studies highlights the need for rigorous evaluation, clinician education, and strategies to support integration of AI-enabled CDSTs into routine practice.
Symon et al. (Fri,) studied this question.