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.

Baylor College of Medicine Dept of Neurosurgery Houston TX USA

Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic

Dartmouth Hitchcock Medical Center Dept of Neurology Lebanon NH USA

Emory University Dept of Neurosurgery Atlanta GA USA

Gdansk University of Technology Faculty of Electronics Telecommunications and Informatics Multimedia Systems Department Gdansk Poland

Mayo Clinic Dept of Neurology Rochester MN USA

Mayo Clinic Dept of Physiology and Biomedical Engineering Rochester MN USA

Thomas Jefferson University Hospital Dept of Neurology Philadelphia PA USA

University of Illinois Dept of Electrical and Computer Engineering Urbana Champaign IL USA

University of Pennsylvania Hospital Dept of Neurology Philadelphia PA USA

UT Southwestern Medical Center Dept of Neurosurgery Dallas TX USA

Zobrazit více v PubMed

Engel AK, et al. Invasive recordings from the human brain: clinical insights and beyond. Nature Reviews Neuroscience. 2005;6(1):35. doi: 10.1038/nrn1585. PubMed DOI

Lhatoo, S D., Kahane, P. & Lüders, H. O. (Eds). Invasive Studies of the Human Epileptic Brain: Principles and Practice. Oxford University Press (2018).

Kucewicz MT, et al. Dissecting gamma frequency activity during human memory processing. Brain. 2017;140(5):1337–1350. doi: 10.1093/brain/awx043. PubMed DOI

Kucewicz, M. T. et al. Human verbal memory encoding is hierarchically distributed in a continuous processing stream. ENeuro 6.1: ENEURO-0214 (2019). PubMed PMC

Lee SA, et al. Electrophysiological signatures of spatial boundaries in the human subiculum. Journal of Neuroscience. 2018;38(13):3265–3272. doi: 10.1523/JNEUROSCI.3216-17.2018. PubMed DOI PMC

Blakely TM, et al. Neural correlates of learning in an electrocorticographic motor-imagery brain-computer interface. Brain-Computer Interfaces. 2014;1.3–4:147–157. doi: 10.1080/2326263X.2014.954183. PubMed DOI PMC

Burke JF, et al. Brain computer interface to enhance episodic memory in human participants. Frontiers in Human Neuroscience. 2015;8:1–10. doi: 10.3389/fnhum.2014.01055. PubMed DOI PMC

Merzagora AR, et al. Repeated stimuli elicit diminished high-gamma electrocorticographic responses. Neuroimage. 2014;85:844–852. doi: 10.1016/j.neuroimage.2013.07.006. PubMed DOI PMC

Henin S, et al. Hippocampal gamma predicts associative memory performance as measured by acute and chronic intracranial EEG. Scientific Reports. 2019;9(1):593. doi: 10.1038/s41598-018-37561-z. PubMed DOI PMC

Düzel E, Will DP, Burgess N. Brain oscillations and memory. Current Opinion in Neurobiology. 2010;20(2):143–149. doi: 10.1016/j.conb.2010.01.004. PubMed DOI

Siegel M, Tobias HD, Andreas KE. Spectral fingerprints of large-scale neuronal interactions. Nature Reviews Neuroscience. 2012;13(2):121–134. doi: 10.1038/nrn3137. PubMed DOI

Buzsáki, G. Rhythms of the Brain. Oxford University Press (2006).

Duun-Henriksen J, et al. Channel selection for automatic seizure detection. Clinical Neurophysiology. 2012;123(1):84–92. doi: 10.1016/j.clinph.2011.06.001. PubMed DOI

Varatharajah Y, et al. Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy. Journal of Neural Engineering. 2018;15(4):046035. doi: 10.1088/1741-2552/aac960. PubMed DOI PMC

Glassman, E L. & John V. G. Reducing the number of channels for an ambulatory patient-specific EEG-based epileptic seizure detector by applying recursive feature elimination. 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2175–2178 (2006). PubMed

Zimbric MR, et al. Three-channel electroencephalogram montage in neonatal seizure detection and quantification. Pediatric Neurology. 2011;44(1):31–34. doi: 10.1016/j.pediatrneurol.2010.08.014. PubMed DOI

Lal, T. N. et al. Methods towards invasive human brain computer interfaces. Advances in Neural Information Processing Systems, 737–744 (2005).

Ansari-Asl, K., Guillaume, C. & Thierry, P. A channel selection method for EEG classification in emotion assessment based on synchronization likelihood. 15th European Signal Processing Conference, 2007. IEEE, 1241–1245 (2007).

Kremen V, et al. Behavioral state classification in epileptic brain using intracranial electrophysiology. Journal of Neural Engineering. 2017;14(2):026001. doi: 10.1088/1741-2552/aa5688. PubMed DOI PMC

Kremen V, et al. Automated unsupervised behavioral state classification using intracranial electrophysiology. Journal of Neural Engineering. 2019;16(2):026004. doi: 10.1088/1741-2552/aae5ab. PubMed DOI

Lan T, et al. Channel selection and feature projection for cognitive load estimation using ambulatory EEG. Computational Intelligence and Neuroscience. 2007;2007(74895):12. PubMed PMC

Schröder M, et al. Robust EEG channel selection across subjects for brain-computer interfaces. EURASIP Journal on Applied Signal Processing. 2005;2005:3103–3112.

Wei Q, et al. Channel selection for optimizing feature extraction in an electrocorticogram-based brain-computer interface. Journal of Clinical Neurophysiology. 2010;27(5):321–327. doi: 10.1097/WNP.0b013e3181f52f2d. PubMed DOI

Yang J, et al. Channel selection and classification of electroencephalogram signals: an artificial neural network and genetic algorithm-based approach. Artificial Intelligence in Medicine. 2012;55(2):117–126. doi: 10.1016/j.artmed.2012.02.001. PubMed DOI

Alotaiby T, et al. A review of channel selection algorithms for EEG signal processing. EURASIP Journal on Advances in Signal Processing. 2015;2015(1):1–21. doi: 10.1186/s13634-015-0251-9. DOI

Zhao, H. B. et al. Channel selection and feature extraction of ECoG-based brain-computer interface using band power. Applied Mechanics and Materials. Vol. 44: 3564–3568. Trans Tech Publications (2011).

Cimbalnik J, Michal TK, Worrell G. Interictal high-frequency oscillations in focal human epilepsy. Current Opinion in Neurology. 2016;29(2):175–81. doi: 10.1097/WCO.0000000000000302. PubMed DOI PMC

Fell J, et al. Human memory formation is accompanied by rhinal–hippocampal coupling and decoupling. Nature Neuroscience. 2001;4(12):1259–64. doi: 10.1038/nn759. PubMed DOI

Binder JR, et al. Where is the semantic system? A critical review and meta-analysis of 120 functional neuroimaging studies. Cerebral Cortex. 2009;19(12):2767–2796. doi: 10.1093/cercor/bhp055. PubMed DOI PMC

Ojemann GA. Cortical organization of language. Journal of Neuroscience. 1991;11(8):2281–2287. doi: 10.1523/JNEUROSCI.11-08-02281.1991. PubMed DOI PMC

Restoring Active Memory (RAM), RAM Public Data Release. Available, http://memory.psych.upenn.edu/RAM (2017).

Kucewicz, M. T. et al. Electrical stimulation modulates high γ activity and human memory performance. ENeuro 5.1: ENEURO-0369 (2018). PubMed PMC

Kahana, M J. Foundations of Human Memory. Oxford University Press (2012).

Kucewicz MT, et al. High frequency oscillations are associated with cognitive processing in human recognition memory. Brain. 2014;137(8):2231–2244. doi: 10.1093/brain/awu149. PubMed DOI PMC

Burke JF, et al. Human intracranial high-frequency activity maps episodic memory formation in space and time. Neuroimage. 2014;85:834–843. doi: 10.1016/j.neuroimage.2013.06.067. PubMed DOI PMC

Ray S, et al. Neural correlates of high-gamma oscillations (60–200 Hz) in macaque local field potentials and their potential implications in electrocorticography. The Journal of Neuroscience. 2008;28(45):11526–11536. doi: 10.1523/JNEUROSCI.2848-08.2008. PubMed DOI PMC

Rich EL, Wallis JD. Spatiotemporal dynamics of information encoding revealed in orbitofrontal high-gamma. Nature Communications. 2017;8:1139. doi: 10.1038/s41467-017-01253-5. PubMed DOI PMC

Watson BO, Ding M, Buzsaki G. Temporal coupling of field potentials and action potentials in the neocortex. European Journal of Neuroscience. 2018;48(7):2482–2497. doi: 10.1111/ejn.13807. PubMed DOI PMC

Logothetis NK, et al. Neurophysiological investigation of the basis of the fMRI signal. Nature. 2001;412:150–157. doi: 10.1038/35084005. PubMed DOI

Jonathan, D. C & Kung-Sik, C Time series analysis with applications in R. SpringerLink, Springer eBooks (2008).

Buzsáki G, da Silva FL. High frequency oscillations in the intact brain. Progress in Neurobiology. 2012;98(3):241–249. doi: 10.1016/j.pneurobio.2012.02.004. PubMed DOI PMC

Jorgenson LA, et al. The BRAIN Initiative: developing technology to catalyse neuroscience discovery. Philosophical Transactions of the Royal Society B: Biological Sciences. 2015;370(1668):20140164. doi: 10.1098/rstb.2014.0164. PubMed DOI PMC

Ezzyat Y, et al. Direct brain stimulation modulates encoding states and memory performance in humans. Current Biology. 2017;27(9):1251–1258. doi: 10.1016/j.cub.2017.03.028. PubMed DOI PMC

Solomon EA, et al. Widespread theta synchrony and high-frequency desynchronization underlies enhanced cognition. Nature. Communications. 2017;8(1):1704. PubMed PMC

Bahramisharif A, et al. Serial representation of items during working memory maintenance at letter-selective cortical sites. PLoS Biology. 2018;16(8):e2003805. doi: 10.1371/journal.pbio.2003805. PubMed DOI PMC

Saboo, K, et al. A computationally-efficient model for predicting successful memory encoding using machine-learning-based channel selection. 9thInternational IEEE/EMBS Conference on Neural Engineering (2019).

Lachaux J‐P, et al. A quantitative study of gamma‐band activity in human intracranial recordings triggered by visual stimuli. European Journal of Neuroscience. 2000;12(7):2608–2622. doi: 10.1046/j.1460-9568.2000.00163.x. PubMed DOI

Jacobs J, Michael JK. Neural representations of individual stimuli in humans revealed by gamma-band electrocorticographic activity. Journal of Neuroscience. 2009;29(33):10203–10214. doi: 10.1523/JNEUROSCI.2187-09.2009. PubMed DOI PMC

Hermes D, Nguyen M, Winawer J. Neuronal synchrony and the relation between the blood-oxygen-level dependent response and the local field potential. PLoS Biology. 2017;15(7):e2001461. doi: 10.1371/journal.pbio.2001461. PubMed DOI PMC

Miller KJ, et al. Spectral changes in cortical surface potentials during motor movement. Journal of Neuroscience. 2007;27(9):2424–2432. doi: 10.1523/JNEUROSCI.3886-06.2007. PubMed DOI PMC

Aoki F, et al. Increased gamma-range activity in human sensorimotor cortex during performance of visuomotor tasks. Clinical Neurophysiology. 1999;110(3):524–537. doi: 10.1016/S1388-2457(98)00064-9. PubMed DOI

Miller KJ, et al. Cortical activity during motor execution, motor imagery, and imagery-based online feedback. Proceedings of the National Academy of Sciences. 2010;107(9):4430–4435. doi: 10.1073/pnas.0913697107. PubMed DOI PMC

Lachaux J-P, et al. High-frequency neural activity and human cognition: past, present and possible future of intracranial EEG research. Progress in neurobiology. 2012;98(3):279–301. doi: 10.1016/j.pneurobio.2012.06.008. PubMed DOI PMC

Phase-Amplitude Coupling Localizes Pathologic Brain with Aid of Behavioral Staging in Sleep

Hotspot of human verbal memory encoding in the left anterior prefrontal cortex

Leveraging electrophysiologic correlates of word encoding to map seizure onset zone in focal epilepsy: Task-dependent changes in epileptiform activity, spectral features, and functional connectivity