1 Seizure prediction — ready for a new era Levin Kuhlmann 1,2,3 , Klaus Lehnertz 4,5 *, Mark P. Richardson 6 , Björn Schelter 7 , Hitten P. Zaveri 8 1 Centre for Human Psychopharmacology, Swinburne University of Technology, Hawthorne, VIC, Australia 2 Department of Medicine – St. Vincent’s, The University of Melbourne, Parkville, VIC, Australia 3 Department of Biomedical Engineering, The University of Melbourne, Parkville, VIC, Australia 4 Department of Epileptology, University of Bonn, Bonn, Germany 5 Interdisciplinary Center for Complex Systems, University of Bonn, Bonn, Germany 6 Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK 7 Institute for Complex Systems and Mathematical Biology, University of Aberdeen, Aberdeen, UK 8 Department of Neurology, Yale University, New Haven, CT, USA *e-mail: Klaus.Lehnertz@ukb.uni-bonn.de 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 has been devoted to the prediction of seizures, aiming to remove the burden of unpredictability and 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 electroencephalography (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, 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 development of seizure prediction technology to instigate development of a solution that removes the burden of the unpredictability of seizures. [H1] Introduction The prevalence of epilepsy is almost 1% worldwide 1 , and in approximately 30% of people with epilepsy, the condition is intractable to anti-epileptic drugs 2 . Medically intractable epilepsy is associated with adverse outcomes, including serious comorbidities, injury and death 3 . Central to the burden of intractable epilepsy is the unpredictability of seizures 4,5 , which is a major detriment to quality of life 6,7 . The ability to accurately predict a seizure minutes before onset would enable patients to take precautions against injury and would open the door to novel timely treatment to pre-empt or control the impending seizure. The field of seizure prediction was established in the 1980s, but after >20 years, a comprehensive review published in 2007 8 concluded that “the current literature allows no definite conclusion as to whether seizures are predictable by prospective algorithms". Nevertheless, in the past decade, several innovations have driven the field forward (Fig. 1), including: recognition that potential