Abstract
Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. We developed an unsupervised, fully automated approach to classify active electrodes showing event-related intracranial EEG (iEEG) responses from 115 patients performing a free recall verbal memory task. Our approach employed new interpretable metrics that quantify spectral characteristics of the normalized iEEG signal based on power-in-band and synchrony measures. Unsupervised clustering of the metrics identified distinct sets of active electrodes across different subjects. In the total population of 11,869 electrodes, our method achieved 97% sensitivity and 92.9% specificity with the most efficient metric. We validated our results with anatomical localization revealing significantly greater distribution of active electrodes in brain regions that support verbal memory processing. We propose our machine-learning framework for objective and efficient classification and interpretation of electrophysiological signals of brain activities supporting memory and cognition.
Highlights
Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions
We assessed the performance of individual features (IP for each band, Smoothness Score (SS) for the two theta bands, and Gamma Consistency (GC) features for the two gamma bands) by using sensitivity and specificity in identifying active electrodes (Fig. 3a) with reference to the “ground truth” set of electrodes established in our previous study via expert manual review[4]
We evaluated the performance of the three metrics, and a combination of all metrics (Table 1), comparing trodes with them with a standard dtheevitawtioonbeosftmfeoarteurthesanid0e.n0t5ifaiecdro(sIsPtγihmaendinGthCe1)maenadn the thresholding step, in which power in the high-gamma band elecwere iadnednatilfliemde. tWriecsocbosmerbviendetdhaecbheisetvseednasistievnitsyitfiovirtythoeftmhroersehothldainn8g5s%te,pwmitehthSoSdb,efionllgotwheedlebaystthseenIPsγithifveea.tTuhree
Summary
Identification of active electrodes that record task-relevant neurophysiological activity is needed for clinical and industrial applications as well as for investigating brain functions. All intracranially implanted electrodes broadly measure brain activity, the neurophysiological activity related to a specific cognitive task is observed in only a subset of electrodes[3,4,5,6,7,8,9] located in the regions of brain associated with attention and the particular task Identification of these “active” electrodes is important both for our understanding of the corresponding physiological processes and for developing better clinical treatments. Despite offering better coverage of the brain surface than the intracranial recordings do, they have lower spatial resolution, and cannot accurately measure high-frequency activity[27] or target deep brain structures Those studies have mainly focused on finding active electrodes for task-related classification problems and have not addressed the physiological relevance of the identified electrodes, leading to manual or semiautomatic identification of active electrodes in iEEG3,4,9,28. Our method’s performance was measured against the results of a blinded, independent expert review who labeled active electrodes; the method was further validated by its demonstrated ability to locate active electrodes in brain regions that support verbal memory[29,30]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
