Meta-Analytic Modeling to Define Decision Thresholds for Cerebrospinal Fluid Heparin-Binding Protein in Healthcare-Associated Ventriculitis and Meningitis.

Background/

Objectives

Healthcare-associated ventriculitis and meningitis (HAVM) is a life-threatening complication of neurosurgical procedures. Conventional cerebrospinal fluid (CSF) indices cannot reliably distinguish bacterial infection from sterile postoperative inflammation, and cultures are frequently delayed or negative. We conducted the first systematic review and meta-analysis to determine the pooled diagnostic accuracy of CSF heparin-binding protein (HBP) for HAVM and to establish clinically actionable decision thresholds.

Methods

PubMed, Embase, the Cochrane Library, and China National Knowledge Infrastructure were searched from inception to 15 February 2026. Risk of bias was assessed using QUADAS-3. Sensitivity and specificity were pooled with a bivariate random-effects model, and heterogeneity was explored through subgroup analyses and metaregression. Thresholds were derived using likelihood ratio (LR)-based and diagmeta cutoff modeling.

Results

Twelve studies (n = 1761) were included. Pooled sensitivity was 0.861 (95% confidence interval [CI]: 0.777-0.917) and specificity was 0.848 (95% CI: 0.781-0.897), with a positive LR (LR+) of 5.65 and a negative LR (LR-) of 0.164. At a 50% pretest probability, post-test probability was increased to 85% by a positive result and reduced to 14% by a negative result. Intracerebral hemorrhage cohorts showed lower accuracy (sensitivity: 0.675, specificity: 0.755), whereas brain tumor-predominant cohorts demonstrated the highest performance (sensitivity: 0.935, specificity: 0.922; p = 0.017). Thresholds of ≥41.3 (rule-in; LR+ ≥10) and ≤30.1 ng/mL (rule-out; LR- ≤0.1) defined clinically actionable decision zones.

Conclusions

CSF HBP provides quantitatively defined rule-in and rule-out thresholds that meaningfully shift the post-test probability and may support antimicrobial decision-making in suspected HAVM. Prospective multicenter validation is warranted.