Analysis of Risk Prediction Models to Identify Patients at High Risk of Urinary Incontinence

Abstract

Introduction: Urinary incontinence (UI) is a common health problem and is often undiagnosed in hospital patients. UI can cause complications such as urinary tract infections, dermatitis, and decreased quality of life. This study aims to apply a risk prediction model to identify patients at high risk of experiencing UI at Tengku Peukan General Hospital, Southwest Aceh, Indonesia.
 Methods: This study used a prospective cohort design. Data was collected from 100 patients hospitalized at Tengku Peukan General Hospital, Southwest Aceh. A risk prediction model was developed using logistic regression. Model performance is measured by AUC-ROC values and accuracy.
 Results: The risk prediction model developed had an AUC-ROC value of 0.85 (95% CI: 0.78-0.92) and an accuracy of 82%. The most significant risk factors for UI are age, gender, history of UI, and use of diuretic medications.
 Conclusion: This risk prediction model can help nurses and doctors identify patients who are at high risk of experiencing UI at Tengku Peukan General Hospital, Southwest Aceh. Early intervention in high-risk patients can help prevent UI complications and improve the patient's quality of life.