RT Journal Article
SR Electronic
T1 Seizure prediction in genetic rat models of absence epilepsy: improved performance through multiple-site cortico-thalamic recordings combined with machine learning
JF eneuro
JO eNeuro
FD Society for Neuroscience
SP ENEURO.0160-21.2021
DO 10.1523/ENEURO.0160-21.2021
A1 Björn Budde
A1 Vladimir Maksimenko
A1 Kelvin Sarink
A1 Thomas Seidenbecher
A1 Gilles van Luijtelaar
A1 Tim Hahn
A1 Hans-Christian Pape
A1 Annika Lüttjohann
YR 2021
UL http://www.eneuro.org/content/early/2021/11/11/ENEURO.0160-21.2021.abstract
AB Seizure prediction is the grand challenge of epileptology. Yet, effort was devoted to prediction of focal seizures, while generalized seizures were regarded as stochastic events. Long lasting LFP recordings containing several hundred generalized spike and wave discharges (SWDs), acquired at eight locations in the cortico-thalamic system of absence epileptic rats, were iteratively analyzed in all possible combinations of either two or three recording sites, by a wavelet-based algorithm, calculating the product of the wavelet-energy signaling increases in synchronicity. Sensitivity and false alarm rate of prediction were compared between various combinations and wavelet spectra of true- and false positive predictions were fed to a random forest machine learning algorithm to further differentiate between them. Wavelet analysis of intracortical and cortico-thalamic LFP traces showed a significantly smaller number of false alarms compared intrathalamic combinations, while predictions based on recordings in layer 4, 5 and 6 of the somatosensory-cortex significantly outreached all other combinations in terms of prediction sensitivity. In 24-hours out-of-sample recordings of 9 GAERS, containing diurnal fluctuations of SWD occurrence, classification of true and false positives by the trained random forest further reduced the false alarm rate by 71%, although at some tradeoff between false alarms and sensitivity of prediction, as reflected in relatively low F1-score values. Results provide support for the cortical-focus theory of absence epilepsy and allow the conclusion that SWDs are predictable to some degree. The latter paves the way for the development of closed-loop SWD prediction-prevention systems. Suggestions for a possible translation to human data are outlined.Significance statementSeizure prediction was declared the grand challenge of epileptology. While most effort was devoted to the prediction of focal seizures, generalized seizures were regarded as stochastic events. Results of this study demonstrate that above chance prediction of generalized spike and wave discharges (SWDs) is possible in long lasting, pseudoprospective 24 hours recordings of absence epileptic rats, by means of wavelet analysis of LFP traces acquired near the proposed cortical initiation network in S1 and further classification of true and false positive detections by a trained random forest machine learning algorithm. Moreover, as lower SWD prediction performance was achieved by analysis of LFP traces distant to S1, the study provides evidence supporting the cortical focus theory of absence epilepsy.