Encoding-related brain activity and accelerated forgetting in transient epileptic amnesia

The accelerated forgetting of newly learned information is common amongst patients with epilepsy and, in particular, in the syndrome of transient epileptic amnesia (TEA). However, the neural mechanisms underlying accelerated forgetting are poorly understood. It has been hypothesised that interictal epileptiform activity during longer retention intervals disrupts normally established memory traces. Here, we tested a distinct hypothesis that accelerated forgetting relates to the abnormal encoding of memories. We studied a group of 15 patients with TEA together with matched, healthy control subjects. Despite normal performance on standard anterograde memory tasks, patients showed accelerated forgetting of a word list over one week. We used a subsequent memory paradigm to compare encoding-related brain activity in patients and controls. Participants studied a series of visually presented scenes whilst undergoing functional MRI scanning. Recognition memory for these scenes was then probed outside the scanner after delays of 45 min and of 4 days. Patients showed poorer memory for the scenes compared with controls. In the patients but not the controls, subsequently forgotten stimuli were associated with reduced hippocampal activation at encoding. Furthermore, patients demonstrated reduced deactivation of posteromedial cortex regions upon viewing subsequently remembered stimuli as compared to subsequently forgotten ones. These data suggest that abnormal encoding-related activity in key memory areas of the brain contributes to accelerated forgetting in TEA. We propose that abnormally encoded memory traces may be particularly vulnerable to interference from subsequently encountered material and hence be forgotten more rapidly. Our results shed light on the mechanisms underlying memory impairment in epilepsy, and offer support to the proposal that accelerated forgetting may be a useful marker of subtle dysfunction in memory-related brain systems. (C) 2018 The Authors. Published by Elsevier Ltd.