High-frequency oscillations in epilepsy and surgical outcome. A meta-analysis

Abstract

High frequency oscillations (HFOs) are estimated as a potential marker for epileptogenicity. Current research strives for valid evidence that these HFOs could aid the delineation of the to-be resected area in patients with refractory epilepsy and improve surgical outcomes. In the present meta-analysis, we evaluated the relation between resection of regions from which HFOs can be detected and outcome after epilepsy surgery. We conducted a systematic review of all studies that related the resection of HFO-generating areas to postsurgical outcome. We related the outcome (seizure freedom) to resection ratio, that is, the ratio between the number of channels on which HFOs were detected and, among these, the number of channels that were inside the resected area. We compared the resection ratio between seizure free and not seizure free patients. In total, 11 studies were included. In 10 studies, ripples (80-200 Hz) were analyzed, and in 7 studies, fast ripples (>200 Hz) were studied. We found comparable differences (dif) and largely overlapping confidence intervals (CI) in resection ratios between outcome groups for ripples (dif = 0.18; CI: 0.10-0.27) and fast ripples (dif = 0.17; CI: 0.01-0.33). Subgroup analysis showed that automated detection (dif = 0.22; CI: 0.03-0.41) was comparable to visual detection (dif = 0.17; CI: 0.08-0.27). Considering frequency of HFOs (dif = 0.24; CI: 0.09-0.38) was related more strongly to outcome than considering each electrode that was showing HFOs (dif = 0.15; CI = 0.03-0.27). The effect sizes found in the meta-analysis are small but significant. Automated detection and application of a detection threshold in order to detect channels with a frequent occurrence of HFOs is important to yield a marker that could be useful in presurgical evaluation. In order to compare studies with different methodological approaches, detailed and standardized reporting is warranted.

Keywords: HFO detection; HFOs; epilepsy surgery; fast ripples; ripples.

Figure 1

Illustration of the zone model as defined by Rosenow and Lüders (2001). There are currently no diagnostic means to unambiguously delineate the epileptogenic zone, so that it needs to be estimated based on various diagnostic measures. HFOs are considered a further piece of information to circumscribe the epileptogenic zone. Ongoing research assesses the degree of correlation of the HFO-generating zone with the other zones, in particular the epileptogenic zone.

Figure 2

Flowchart illustrating the systematic search of literature and the selection process of articles. We want to mention that 4 articles were considered to be relevant, but excluded already on the basis of the whole text because of non-quantitative reporting of results (Ramachandrannair et al., ; Wu et al., ; Nariai et al., ; Iwatani et al., 2012).

Figure 3

Meta-analysis results for ripples. The resection ratio for ripples is higher in seizure free patients compared to non-seizure free patients. For each study, a graphical representation of the effect (i.e., the difference of the resection ratio between the good- and bad-outcome group) and of the confidence interval (CI) is given along with the exact values (EV) and the weights.

Figure 4

Meta-analysis results for fast ripples. The resection ratio is higher in seizure free patients compared to non-seizure free patients. For each study, a graphical representation of the effect (i.e., the difference of the resection ratio between the good- and bad-outcome group) and of the confidence interval (CI) is given along with the exact values (EV) and the weights.

Figure 5

Funnel plot for analysis of publication bias for ripples. There is no asymmetry pointing toward missing studies on the left side of the plot.

Figure 6

Funnel plot for analysis of publication bias for fast ripples. There is no asymmetry pointing toward missing studies on the left side of the plot.