Systematic review and meta-analysis of the duration of clinical effect of onabotulinumtoxinA in cervical dystonia

Abstract

Background: Botulinum toxins are considered first-line therapy for treatment of cervical dystonia (CD) and must be injected on a repeat basis. Understanding the duration of clinical benefit of botulinum toxins and its impact on health care utilization are thus important in the contemporary environment. However, there is currently no overall consensus on the duration of effect of onabotulinumtoxinA in the treatment of CD. We performed a systematic review and meta-analysis to identify the duration of effect of onabotulinumtoxinA in CD and investigate factors that may influence it.

Methods: A systematic literature search identified prospective or retrospective studies reporting duration of effect of onabotulinumtoxinA for the treatment of CD. Inclusion criteria included peer-reviewed, non-review, English-language articles published between January 1980 and January 2013. A formal meta-analysis using Comprehensive Meta-Analysis Version 2 was conducted to identify the duration of effect of onabotulinumtoxinA in the treatment of CD; both fixed and random effects models were performed. Subgroup analyses were performed to identify factors that influenced the duration of effect of onabotulinumtoxinA.

Results: A total of 18 studies (including >1,900 patients) met the inclusion criteria and were used for the meta-analysis. The mean duration of effect of onabotulinumtoxinA in CD was found to be 93.2 days (95% CI 91.8-94.6 days) for the fixed effects model and 95.2 days (95% CI 88.9-101.4 days) for the random effects model. A meta-regression found that dose of onabotulinumtoxinA and country of origin influenced the duration of effect of onabotulinumtoxinA, whereas quality score of the article and study type did not. In particular, doses ≥180 Units were associated with longer durations of effect than doses <180 Units (107-109 days vs. 86-88 days, respectively; p < 0.01). Limitations included pooling studies that used discrete definitions of duration and had different designs and study quality.

Conclusions: Based on the published literature, the mean duration of effect of onabotulinumtoxinA in CD was 93-95 days (13.2-13.5 weeks). This suggests that, in general, patients with CD treated with onabotulinumtoxinA should require ~4 treatments per year.

Figure 1

Flow diagram showing systematic search strategy and selection of articles.

Figure 2

Regression of quality score on mean duration.

Figure 3

Regression of mean dose on mean duration.

Figure 4

Funnel plot of standard error by mean duration.