Time to prerandomization monthly seizure count in perampanel trials: A novel epilepsy endpoint

Abstract

Objective: To determine whether a novel endpoint of time to prerandomization monthly seizure count could be used to differentiate efficacious and nonefficacious therapies in clinical trials of new add-on antiepileptic drugs (AEDs).

Methods: This analysis used data from 3 randomized, double-blind, placebo-controlled phase III trials of perampanel as an add-on therapy in patients with epilepsy who were experiencing refractory partial seizures: studies 304 (ClinicalTrials.gov identifier NCT00699972), 305 (NCT00699582), and 306 (NCT00700310). Time to prerandomization monthly seizure count was evaluated post hoc for each trial, and findings were compared with the original primary outcomes (median percent change in seizure frequency and 50% responder rate). Outcomes were assessed for all partial-onset seizures, secondarily generalized (SG) tonic-clonic seizures only, and complex partial plus SG (CP + SG) seizures.

Results: Perampanel 4-12 mg significantly prolonged median time to prerandomization monthly seizure count, generally by more than 1 week, compared with placebo, across all 3 studies, consistent with the original primary outcomes. Analysis of SG seizures only, and CP + SG seizures, also indicated a significantly prolonged median time to prerandomization monthly seizure count with perampanel 8 mg and 12 mg compared with placebo.

Conclusions: Time to prerandomization monthly seizure count is a promising novel alternative to the standard endpoints of median percent change in seizure frequency and 50% responder rates used in trials of add-on AEDs. Use of this endpoint could reduce exposure to placebo or ineffective treatments, thereby facilitating trial recruitment and improving safety.

Figure 1. Design of study 306

Studies 304 and 305 were based on similar designs, but with patients randomized to placebo or daily perampanel doses of 8 or 12 mg.

Figure 2. Probability of not achieving prerandomization monthly seizure count in the double-blind treatment phase

Kaplan-Meier curves show probability, with 95% confidence limits (shading) and censored data points (vertical lines), for all partial-onset seizures and secondarily generalized seizures in the double-blind treatment phases of studies 304, 305, and 306.