Validating a Clinical Prediction Rule for Ventricular Shunt Malfunction.

Abstract

This study aims to validate a published ventricular shunt clinical prediction rule for the identification of children at low risk for ventricular shunt malfunction based on the absence of 3 high-risk clinical predictors (irritability, nausea or vomiting, and headache). We identified children aged 21 years and younger with a ventricular shunt who presented between 2010 and 2013 to a single pediatric emergency department (ED) for evaluation of potential shunt malfunction. We defined a ventricular shunt malfunction as obstruction to cerebrospinal fluid flow requiring operative neurosurgical intervention within 72 hours of initial ED evaluation. We applied this ventricular shunt clinical prediction rule to the study population and report the test characteristics. We identified 755 ED visits for 294 children with potential ventricular shunt malfunction. Of these encounters, 146 (19%; 95% confidence interval [CI], 17%-22%) had a ventricular shunt malfunction. The ventricular shunt clinical prediction rule had a sensitivity of 99% (95% CI, 94%-100%), specificity of 7% (95% CI, 5%-9%), and negative predictive value of 95% (95% CI, 82%-99%). Two children with a ventricular shunt malfunction were misclassified as low risk by this clinical prediction rule. Ventricular shunt malfunctions were common. Although children classified as low risk by the ventricular shunt clinical prediction rule were less likely to have a shunt malfunction, routine neuroimaging may still be required because exclusion of ventricular shunt malfunction may be difficult on clinical grounds alone.