Seizure prediction — ready for a new era

Abstract

Epilepsy is a common disorder characterized by recurrent seizures. An overwhelming majority of people with epilepsy regard the unpredictability of seizures as a major issue. More than 30 years of international effort have been devoted to the prediction of seizures, aiming to remove the burden of unpredictability and to couple novel, time-specific treatment to seizure prediction technology. A highly influential review published in 2007 concluded that insufficient evidence indicated that seizures could be predicted. Since then, several advances have been made, including successful prospective seizure prediction using intracranial EEG in a small number of people in a trial of a real-time seizure prediction device. In this Review, we examine advances in the field, including EEG databases, seizure prediction competitions, the prospective trial mentioned and advances in our understanding of the mechanisms of seizures. We argue that these advances, together with statistical evaluations, set the stage for a resurgence in efforts towards the development of seizure prediction methodologies. We propose new avenues of investigation involving a synergy between mechanisms, models, data, devices and algorithms and refine the existing guidelines for the development of seizure prediction technology to instigate development of a solution that removes the burden of the unpredictability of seizures.

Ensembling crowdsourced seizure prediction algorithms using long‐term human intracranial EEG

“…Moreover, algorithms that directly account for known seizure triggers, such as sleep-wake rhythms, as well as novel measurement approaches may offer alternative routes to performance gains. 2,3,16 In addition, recent work looking at long-term rhythms 18 holds significant promise for seizure forecasting, could be applied in the machine learning context, and suggests that the performance limits seen here may not be tied to potential limits imposed by the physiologic processes underlying seizure occurrence.…”

“…It is also very important to note that as a result of Kaggle contest formats, contestants did not have full timing information available to them for training, such as the time of interictal segments relative to preictal segments, which may significantly limit algorithm performance. Moreover, algorithms that directly account for known seizure triggers, such as sleep‐wake rhythms, as well as novel measurement approaches may offer alternative routes to performance gains . In addition, recent work looking at long‐term rhythms holds significant promise for seizure forecasting, could be applied in the machine learning context, and suggests that the performance limits seen here may not be tied to potential limits imposed by the physiologic processes underlying seizure occurrence.…”

“…Methods for accurate seizure prediction have the potential to transform epilepsy management by offering warnings to patients or triggering interventions. [1][2][3] Prospective seizure prediction has been shown to be feasible using long-term intracranial electroencephalography (iEEG) recordings obtained during the first-in-human trial of a seizure prediction device; however, prediction accuracy should be increased for a broader range of patients in order to demonstrate clinical utility. 4 Several studies have looked at achieving retrospective improvements with the same long-term data.…”

Critical slowing as a biomarker for seizure susceptibility

“…In this work, we use the markers of critical slowing as a proxy to track the slow parameter k that, in turn, offers a biomarker for seizure susceptibility [3]. Moreover, we focus on seizure forecasting [3,27] rather than seizure prediction [2], as we do not attempt to predict the fast (noise) event that perturbs the system towards the seizure state.…”

“…The mechanisms underlying the transition from a normal to a seizure state are currently an open question [2][3][4]. Unravelling the mechanisms underlying seizure generation could form the basis of much needed new treatment strategies, particularly for patients where existing treatments are ineffective.…”