Controlled Pilot Intervention Study on the Effects of an AI‐Based Application to Support Incontinence‐Associated Dermatitis and Pressure Injury Assessment, Nursing Care and Documentation: Study Protocol

Artificial Intelligence (AI)-based applications have significant potential to differentiate between pressure injuries (PI) and incontinence-associated dermatitis (IAD), common challenges in nursing practice. Within the KIADEKU overall project, we are developing an AI-based application to aid in the nursing care of PI and IAD and to facilitate personalized, evidence-based nursing interventions. The KIADEKU clinical sub-study described in this study protocol is a controlled, non-randomized clinical pilot intervention study investigating the effects of the AI-based application, fully developed in the KIADEKU overall project, on the duration of wound assessment, dressing change and documentation, guideline adherence, and nurse task load. The study utilizes a pre-post design with two data collection periods. During the initial phase, we will observe and survey nurses in the control group as they provide conventional wound care without AI support to adult patients with PI or IAD in the pelvic area across eight wards at the LMU University Hospital. In the following intervention phase, the AI-based application will assist nurses in wound assessment and deliver guideline-based nursing interventions for documented wound types. Observations and surveys will be repeated. Measurements will include the duration of wound assessment, dressing changes, and documentation, adherence to wound care guidelines, and the accuracy of AI predictions in clinical settings, validated by an on-site expert assessment. The survey will assess nurses' task load and other covariates, such as professional experience, overall workload during the shift, and wound severity. Linear regression models will be used to analyze the effects of AI usage on the aforementioned aspects, taking into account these covariates. The accuracy of AI predictions regarding wound type and classification will be measured using the on-site expert's assessment as the ground truth. The usability of the AI-based application and standard clinical documentation systems will be evaluated further. The deployment of the AI application in clinical settings aims to reduce the duration of wound assessments, dressing changes, and documentation; decrease nurse task load; enhance guideline adherence in wound care; and promote AI utilization in nursing. German Clinical Trials Register (DRKS) (DRKS00031355). Registered on April 5th, 2023. TRIAL REGISTRATION: German Clinical Trials Register (DRKS) DRKS00031355. Registered on April 5^th 2023. PATIENT OR PUBLIC CONTRIBUTION: Patient representatives contributed to the development of the AI-based application through the use of Delphi methodology, as part of the KIADEKU qualitative sub-study.