Early hyperbaric oxygen therapy is associated with favorable outcome in patients with iatrogenic cerebral arterial gas embolism: systematic review and individual patient data meta-analysis of observational studies

Abstract

Background: Iatrogenic cerebral arterial gas embolism (CAGE) caused by invasive medical procedures may be treated with hyperbaric oxygen therapy (HBOT). Previous studies suggested that initiation of HBOT within 6-8 h is associated with higher probability of favorable outcome, when compared to time-to-HBOT beyond 8 h. We performed a group level and individual patient level meta-analysis of observational studies, to evaluate the relationship between time-to-HBOT and outcome after iatrogenic CAGE.

Methods: We systematically searched for studies reporting on time-to-HBOT and outcome in patients with iatrogenic CAGE. On group level, we meta-analyzed the differences between median time-to-HBOT in patients with favorable versus unfavorable outcome. On individual patient level, we analyzed the relationship between time-to-HBOT and probability of favorable outcome in a generalized linear mixed effects model.

Results: Group level meta-analysis (ten studies, 263 patients) shows that patients with favorable outcome were treated with HBOT 2.4 h (95% CI 0.6-9.7) earlier than patients with unfavorable outcome. The generalized linear mixed effects model (eight studies, 126 patients) shows a significant relationship between time-to-HBOT and probability of favorable outcome (p = 0.013) that remains significant after correcting for severity of manifestations (p = 0.041). Probability of favorable outcome decreases from approximately 65% when HBOT is started immediately, to 30% when HBOT is delayed for 15 h.

Conclusions: Increased time-to-HBOT is associated with decreased probability of favorable outcome in iatrogenic CAGE. This suggests that early initiation of HBOT in iatrogenic CAGE is of vital importance.

Keywords: Air embolism; Embolic stroke; Hyperbaric oxygenation; Iatrogenic disease.

Fig. 1

PRISMA diagram

Fig. 2

Graphical results of the generalized linear model, with probability of favorable outcome plotted in relation to time-to-HBOT. Dashed lines are 95% confidence intervals. The left-hand figure A displays the data with the delay plotted up to 150 h, whereas the figure on the right B shows the same data but zoomed in to a timeframe of 30 h, in order to show the first hours in more detail