Pedro F Viana1,2,3, Tal Pal Attia4, Mona Nasseri4,5, Jonas Duun-Henriksen6, Andrea Biondi1,2, Joel S Winston1,2, Isabel Pavão Martins3, Ewan S Nurse7,8, Matthias Dümpelmann9, Andreas Schulze-Bonhage9, Dean R Freestone7,8, Troels W Kjaer10,11, Mark P Richardson1,2,12, Benjamin H Brinkmann4. 1. School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK. 2. Centre for Epilepsy, King's College Hospital National Health Service Foundation Trust, London, UK. 3. Faculty of Medicine, University of Lisbon, Lisbon, Portugal. 4. Bioelectronics Neurology and Engineering Laboratory, Department of Neurology, Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, Minnesota, USA. 5. School of Engineering, University of North Florida, Jacksonville, Florida, USA. 6. UNEEG medical, Lillerød, Denmark. 7. Seer Medical, Melbourne, Victoria, Australia. 8. Department of Medicine, University of Melbourne, Melbourne, Victoria, Australia. 9. Epilepsy Center, Department for Neurosurgery, University Medical Center Freiburg, Freiburg, Germany. 10. Department of Neurology, Zealand University Hospital, Roskilde, Denmark. 11. Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark. 12. National Institute for Health Research Biomedical Research Centre at South London and Maudsley National Health Service Foundation Trust, London, UK.
Abstract
OBJECTIVE: One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. METHODS: We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. RESULTS: Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. SIGNIFICANCE: This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.
OBJECTIVE: One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. METHODS: We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. RESULTS: Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. SIGNIFICANCE: This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.
Authors: Philippa J Karoly; Dean R Freestone; Ray Boston; David B Grayden; David Himes; Kent Leyde; Udaya Seneviratne; Samuel Berkovic; Terence O'Brien; Mark J Cook Journal: Brain Date: 2016-02-17 Impact factor: 13.501
Authors: Hoameng Ung; Steven N Baldassano; Hank Bink; Abba M Krieger; Shawniqua Williams; Flavia Vitale; Chengyuan Wu; Dean Freestone; Ewan Nurse; Kent Leyde; Kathryn A Davis; Mark Cook; Brian Litt Journal: J Neural Eng Date: 2017-09-01 Impact factor: 5.379
Authors: Ralph G Andrzejak; Florian Mormann; Thomas Kreuz; Christoph Rieke; Alexander Kraskov; Christian E Elger; Klaus Lehnertz Journal: Phys Rev E Stat Nonlin Soft Matter Phys Date: 2003-01-07
Authors: Levin Kuhlmann; Philippa Karoly; Dean R Freestone; Benjamin H Brinkmann; Andriy Temko; Alexandre Barachant; Feng Li; Gilberto Titericz; Brian W Lang; Daniel Lavery; Kelly Roman; Derek Broadhead; Scott Dobson; Gareth Jones; Qingnan Tang; Irina Ivanenko; Oleg Panichev; Timothée Proix; Michal Náhlík; Daniel B Grunberg; Chip Reuben; Gregory Worrell; Brian Litt; David T J Liley; David B Grayden; Mark J Cook Journal: Brain Date: 2018-09-01 Impact factor: 13.501
Authors: Sirin W Gangstad; Kaare B Mikkelsen; Preben Kidmose; Yousef R Tabar; Sigge Weisdorf; Maja H Lauritzen; Martin C Hemmsen; Lars K Hansen; Troels W Kjaer; Jonas Duun-Henriksen Journal: Biomed Eng Online Date: 2019-10-30 Impact factor: 2.819