Risk Prediction Model for Incontinence‐Associated Dermatitis in Critically Ill Patients: A Systematic Review and Meta‐Analysis

BACKGROUND: Incontinence-associated dermatitis (IAD) is a prevalent and distressing skin complication in critically ill patients, leading to increased pain, infection risk and healthcare costs. While several risk prediction models have been developed to guide IAD prevention, their methodological quality, predictive performance and clinical utility remain unclear. A systematic synthesis and evaluation of these models is currently lacking. AIM: This study aimed to systematically review and meta-analysis existing risk prediction models for IAD in critically ill patients, critically appraising their methodological rigour and summarizing their predictive performance. STUDY DESIGN: We searched PubMed, Embase, The Cochrane Library, Web of Science, CINAHL and Chinese databases (CNKI, WanFang, Weipu and SinoMed) from inception to January 2026 for studies developing or validating multivariable prediction models for IAD in adult ICU patients. Two reviewers independently screened records, extracted data and assessed risk of bias using the PROBAST tool. A meta-analysis of pooled AUC values was performed in Stata 15.0 when sufficient quantitative data were available. RESULTS: A total of 834 records screened, 14 studies encompassing 14 prediction models were included. The models demonstrated good to excellent discrimination, with AUC values ranging from 0.810 to 0.993. The most frequently reported predictors across studies were the PAT score, stool frequency, age and serum albumin. Meta-analysis yielded a pooled AUC of 0.88 (95% CI: 0.84-0.91). However, all studies were rated at high risk of bias on the PROBAST tool, primarily due to analytical limitations and participant selection issues. CONCLUSION: Current risk prediction models for incontinence-associated dermatitis in critically ill patients show good discriminative ability but are limited by methodological shortcomings. Future research should focus on developing models with high-quality prospective data and rigorous external validation. A well-validated tool would help ICU teams identify high-risk patients early and improve preventive care. RELEVANCE TO CLINICAL PRACTICE: This review provides a comprehensive synthesis of existing prediction models, offering clinicians a consolidated overview of tools to identify ICU patients at highest risk for IAD, thereby supporting targeted prevention. REVIEW REGISTRATION: CRD420261282052.