Paediatric ventriculoperitoneal shunt obstruction and cerebrospinal fluid protein

Abstract

Background: Ventriculoperitoneal shunt (VPS) insertion is a life-saving intervention for hydrocephalus. Device failure is extremely common, and carries immense morbidity for patients, their families, and the healthcare system. Predicting shunt obstruction remains a substantial challenge. Clinically, cerebrospinal fluid protein (CSFp) is suspected to contribute to VPS obstruction, this is widely debated, and definitive evidence is lacking. We assess the relationship of CSFp in predicting VPS failure in children.

Methods: A retrospective review of VPS procedures at the Queensland Children's Hospital between 2014-2019 was conducted. The relationship between CSFp level and outcome were explored. A conventional CSFp threshold above 500 mg/L is considered elevated, however a continuous relationship was assessed to better describe concentration associations. Outcome variables were early (<90-days) and late VPS obstruction (<1-year). A CNS infection was reason for exclusion. A logarithmic correction was applied to CSFp (Log-CSFp) for statistical modelling.

Results: 552 procedures were assessed in 243 patients. Fifty-eight (10.5 %) VP shunts obstructed within 90-days, 87 (15.8 %) within 1-year. 63 patients (25.9 %) experienced an episode of <1-year VPS obstruction. Multivariate analysis found Log-CSFp was predictive for early VPS obstruction (OR 1.40, 1.20-1.63, p < 0.0001), and late VPS obstruction (OR 1.37, 1.17-1.62, p < 0.0001) independent to hydrocephalus aetiology, patient age, and CSF red blood cell count. Older patient age was a significant protective factor for late VPS obstruction (OR 0.89, 0.82-0.96, p = 0.002).

Conclusions: CSFp holds prognostic value for VPS obstruction in paediatric patients, a relentlessly unpredictable complication of VPS devices, informing procedure timing, patient follow-up and risk-stratification.

Keywords: CSF Protein; Hydrocephalus; Obstruction; Shunt failure.