Exploratory Analysis of Factors Associated With Pressure Injuries in Surgical Patients Assessed With the ELPO Scale

OBJECTIVE: The objective of this study is to analyse predictors associated with pressure injury occurrence and to explore the relationship between preventive resources and pressure injury outcomes in surgical patients assessed with the ELPO Scale. METHODS: A retrospective cross-sectional study was conducted in a university hospital surgical centre in Brazil. Data from 2698 adult surgical patients (2020-2022) were analysed. Variables included the ELPO score, surgical characteristics, preventive resources and clinical factors. Logistic regression, Random Forest and decision tree (CART) models were applied. Performance was assessed using AUC, sensitivity, specificity, positive predictive value, negative predictive value and F1 score. RESULTS: The incidence of PI was 2.9%. Male sex (OR = 1.74), lateral surgical position (OR = 4.75) and use of a thermal mattress (OR = 2.11) were associated with increased risk. Surgical time ≥ 2 h was associated with lower odds of pressure injury occurrence in the adjusted model. A greater number of cushions was associated with reduced pressure injury occurrence in unadjusted analyses; however, this association was not consistently maintained after multivariable adjustment. Predictive models demonstrated limited discriminative performance (AUC≈0.60). The ELPO total score was the most influential predictor. CONCLUSIONS: ELPO-based assessment and structured perioperative risk evaluation may support perioperative risk assessment and identification of patients at higher risk of pressure injury; however, the predictive models should be considered exploratory and require external validation.