Machine Learning to Classify Relative Seizure Frequency From Chronic Electrocorticography.

Brain responsive neurostimulation (NeuroPace) treats patients with refractory focal epilepsy and provides chronic electrocorticography (ECoG). We explored how machine learning algorithms applied to interictal ECoG could assess clinical response to changes in neurostimulation parameters. We identified five responsive neurostimulation patients each with ≥200 continuous days of stable medication and detection settings (median, 358 days per patient). For each patient, interictal ECoG segments for each month were labeled as "high" or "low" to represent relatively high or low long-episode (i.e., seizure) count compared with the median monthly long-episode count. Power from six conventional frequency bands from four responsive neurostimulation channels were extracted as features. For each patient, five machine learning algorithms were trained on 80% of ECoG, then tested on the remaining 20%. Classifiers were scored by the area-under-the-receiver-operating-characteristic curve. We explored how individual circadian cycles of seizure activity could inform classifier building. Support vector machine or gradient boosting models achieved the best performance, ranging from 0.705 (fair) to 0.892 (excellent) across patients. High gamma power was the most important feature, tending to decrease during low-seizure-frequency epochs. For two subjects, training on ECoG recorded during the circadian ictal peak resulted in comparable model performance, despite less data used. Machine learning analysis on retrospective background ECoG can classify relative seizure frequency for an individual patient. High gamma power was the most informative, whereas individual circadian patterns of seizure activity can guide model building. Machine learning classifiers built on interictal ECoG may guide stimulation programming.

Informations de copyright

Copyright © 2021 by the American Clinical Neurophysiology Society.

Déclaration de conflit d'intérêts

P. Dugan and A. Liu have received speaking honoraria from Neuropace. A. Liu has consulted for the ECRI Institute. D. Friedman receives salary support for consulting and clinical trial–related activities performed on behalf of The Epilepsy Study Consortium, a nonprofit organization. Within the past two years, The Epilepsy Study Consortium received payments for research services performed by D. Friedman from Axcella, Biogen, Cerevel, Crossject, Engage Pharmaceuticals, Eisai, Pfizer, SK Life Science, Xenon, and Zynerba; he has also served as a paid consultant for Eisai and Neurelis Pharmaceuticals; he has received travel support from Medtronics, Eisai, and the Epilepsy Foundation; he has received research support from the CDC, NINDS, Epilepsy Foundation, Empatica, Epitel, UCB, Inc, and Neuropace; he serves on the scientific advisory board for Receptor Life Sciences; and he holds equity interests in Neuroview Technology and Receptor Life Sciences. The remaining authors have no conflict of interest to disclose.