Pitfalls of using video-EEG for a trial endpoint in children aged <4 years with focal seizures

Objective Double-blind, randomized, and placebo-controlled trial SP0967 (NCT02477839/2013-000717-20) did not demonstrate superior efficacy of lacosamide versus placebo in patients aged >= 1 month to <4 years with uncontrolled focal seizures, per <= 72 h video-electroencephalogram (video-EEG)-based primary endpoints (reduction in average daily frequency of focal seizures at end-of-maintenance [EOM] versus end-of-baseline [EOB], patients with >= 50% response). This was unexpected because randomized controlled trial SP0969 (NCT01921205) showed efficacy of lacosamide in patients aged >= 4 to <17 years with uncontrolled focal seizures. SP0969's primary endpoint was based on seizure diary instead of video-EEG, an issue with the latter being inter-reader variability. We evaluated inter-reader agreement in video-EEG interpretation in SP0967, which to our knowledge, are the first such data for very young children with focal seizures from a placebo-controlled trial. Methods Local investigator and central reader agreement in video-EEG interpretation was analyzed post hoc. Results Analysis included 105 EOB and 98 EOM video-EEGs. Local investigators and central reader showed poor agreement based on >= 2 focal seizures at EOB (Kappa = 0.01), and fair agreement based on >= 2 focal seizures at EOM (Kappa = 0.23). Local investigator and central reader seizure count interpretations varied substantially, particularly for focal seizures, but also primary generalized and unclassified epileptic seizures, at both timepoints. Interpretation High inter-reader variability and low inter-reader reliability of the interpretation of seizure types and counts prevent confident conclusion regarding the lack of efficacy of lacosamide in this population. We recommend studies in very young children do not employ video-EEGs exclusively for accurate study inclusion or as an efficacy measure.