Dexamethasone in adults with viral meningitis: an observational cohort study

Abstract

Objectives: To investigate whether there is a dose-dependent association between empiric dexamethasone and outcome in viral meningitis.

Methods: Observational cohort study of adults hospitalized for viral meningitis, both with and without a microbiologically confirmed diagnosis, in Denmark between 2015 and 2020. Dose-dependent associations between dexamethasone (one dose = 10 mg) and an unfavourable outcome (Glasgow Outcome Scale score 1-4) at 30 days after discharge were assessed using weighted logistic regression. Entropy balancing was used to compute weights.

Results: Of 1025 included patients, 658 (64%) did not receive dexamethasone, 115 (11%) received 1-2 doses, 131 (13%) received 3-4 doses, and 121 (12%) received ≥5 doses. Among patients treated with dexamethasone, the median number of doses was higher for those without an identified pathogen than for those with a microbiologically confirmed viral aetiology (5 [interquartile range (IQR) 3-8] vs. 3 [IQR 2-5]; p < 0.001). Using no doses of dexamethasone as a reference, the weighted OR for an unfavourable outcome were 0.55 (95% CI, 0.29-1.07) for 1-2 doses, 1.13 (95% CI, 0.67-1.89) for 3-4 doses, and 1.43 (95% CI, 0.77-2.64) for ≥5 doses. In the subgroup of enteroviral meningitis, the weighted OR was 3.08 (95% CI, 1.36-6.94) for ≥5 doses, but decreased to 2.35 (95% CI, 0.65-8.40) when the reference group was restricted to patients treated with antibiotics for suspected bacterial meningitis.

Discussion: This study showed no dose-dependent association between dexamethasone and an unfavourable outcome in patients with viral meningitis. In enteroviral meningitis, ≥5 doses were associated with an increased risk of an unfavourable outcome. However, sensitivity analysis indicated that the association was affected by unmeasured or residual confounding by severity.

Keywords: Aseptic meningitis; Enterovirus; Glucocorticoids; Herpesviridae; Virology.