Objective: To identify the most important risk factors for predicting pressure injury (PI) occurrence in adult orthopaedic surgical patients based on investigation data, thereby identifying at-risk patients and facilitating formulation of an effective patient care strategy.
Method: Patients were assessed with an instrument designed by the authors specifically for this study in a cross-sectional investigation following the STROBE checklist. The random forest method was adopted to select the most important risk factors and predict occurrence of PIs.
Results: A dataset of 27 risk factors from 1701 patients was obtained. A subset of the 15 most important risk factors was identified. The random forest method had a high prediction accuracy of 0.9733 compared with 0.9281 calculated with a logistic model.
Conclusion: Results indicated that the selected 15 risk factors, such as activity ability, friction/shear force, skin type and anaesthesia score, performed very well in predicting the occurrence of PIs in adult orthopaedic surgical patients.
Keywords: assessment instrument; orthopaedic surgery; pressure injury; random forest; risk factor; wound; wound care; wound dressing; wound healing.