Machine learning classifiers for electrode selection in the design of closed-loop neuromodulation devices for episodic memory improvement.

Publisher: Oxford University Press Country of Publication: United States NLM ID: 9110718 Publication Model: Print Cited Medium: Internet ISSN: 1460-2199 (Electronic) Linking ISSN: 10473211 NLM ISO Abbreviation: Cereb Cortex Subsets: MEDLINE

Original Publication: New York, NY : Oxford University Press, c1991-

Brain*/physiology ; Electrodes*/standards ; Electroencephalography*/methods ; Electroencephalography*/standards ; Memory, Episodic* ; Random Forest* ; Support Vector Machine*; Humans ; Brain-Computer Interfaces ; Cluster Analysis ; Mental Recall ; Unsupervised Machine Learning

Successful neuromodulation approaches to alter episodic memory require closed-loop stimulation predicated on the effective classification of brain states. The practical implementation of such strategies requires prior decisions regarding electrode implantation locations. Using a data-driven approach, we employ support vector machine (SVM) classifiers to identify high-yield brain targets on a large data set of 75 human intracranial electroencephalogram subjects performing the free recall (FR) task. Further, we address whether the conserved brain regions provide effective classification in an alternate (associative) memory paradigm along with FR, as well as testing unsupervised classification methods that may be a useful adjunct to clinical device implementation. Finally, we use random forest models to classify functional brain states, differentiating encoding versus retrieval versus non-memory behavior such as rest and mathematical processing. We then test how regions that exhibit good classification for the likelihood of recall success in the SVM models overlap with regions that differentiate functional brain states in the random forest models. Finally, we lay out how these data may be used in the design of neuromodulation devices.
(© The Author(s) 2023. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: [email protected].)

Psychiatry Res Neuroimaging. 2017 Mar 30;261:72-74. (PMID: 28142056)
IEEE Trans Biomed Eng. 2006 Dec;53(12 Pt 1):2501-6. (PMID: 17153207)
J Neural Eng. 2018 Dec;15(6):066007. (PMID: 30221624)
Neuroimage. 2022 Feb 15;247:118851. (PMID: 34954026)
J Neural Eng. 2019 Feb;16(1):011001. (PMID: 30523919)
Biol Psychiatry. 2022 Aug 1;92(3):246-251. (PMID: 35063186)
Brain. 1982 Jun;105(Pt 2):349-71. (PMID: 7082994)
Neurobiol Aging. 2016 Jun;42:163-76. (PMID: 27143433)
Brain Lang. 1978 May;5(3):331-40. (PMID: 656902)
J Neurosci. 2021 Jun 15;:. (PMID: 34131036)
Int J Psychophysiol. 2003 May;48(2):141-6. (PMID: 12763571)
Front Neurosci. 2018 Nov 01;12:790. (PMID: 30443203)
Nat Neurosci. 2013 Sep;16(9):1188-90. (PMID: 23912946)
Psychol Sci. 2007 Nov;18(11):927-32. (PMID: 17958703)
Brain Res. 2015 Oct 22;1624:286-296. (PMID: 26236022)
Hippocampus. 2012 Apr;22(4):748-61. (PMID: 21538660)
J Neural Eng. 2007 Jun;4(2):R1-R13. (PMID: 17409472)
Nat Commun. 2017 Nov 22;8(1):1704. (PMID: 29167419)
Sensors (Basel). 2014 Jul 17;14(7):12784-802. (PMID: 25036334)
Philos Trans R Soc Lond B Biol Sci. 2002 Aug 29;357(1424):1097-110. (PMID: 12217177)
Sci Rep. 2019 Nov 22;9(1):17390. (PMID: 31758077)
Curr Opin Neurobiol. 2013 Apr;23(2):255-60. (PMID: 23206590)
Trends Cogn Sci. 2003 Jul;7(7):313-319. (PMID: 12860190)
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:656-659. (PMID: 31945983)
Curr Pharm Biotechnol. 2019;20(9):755-765. (PMID: 31258079)
J Neural Eng. 2018 Dec;15(6):066028. (PMID: 30211695)
Neurosurgery. 2021 Jul 15;89(2):E116-E121. (PMID: 33913499)
Hippocampus. 2021 May;31(5):481-492. (PMID: 33544408)
Nat Commun. 2018 Feb 6;9(1):365. (PMID: 29410414)
Brain. 2018 Apr 1;141(4):971-978. (PMID: 29324988)
Brain. 2023 Jan 5;146(1):20-41. (PMID: 36331542)
Neuron. 2016 Dec 7;92(5):983-990. (PMID: 27930911)
IEEE Trans Neural Syst Rehabil Eng. 2022;30:2242-2253. (PMID: 35849675)
Brain Commun. 2020 Dec 15;3(1):fcaa202. (PMID: 33543140)
Neuroimage. 2020 Feb 15;207:116397. (PMID: 31770638)
Comput Methods Programs Biomed. 2012 Oct;108(1):10-9. (PMID: 22178068)
Prog Brain Res. 2008;169:339-52. (PMID: 18394485)
Neurosci Biobehav Rev. 2010 Jun;34(7):1015-22. (PMID: 20006645)
Nature. 2021 May;593(7858):249-254. (PMID: 33981047)
J Neurosci. 2014 Aug 20;34(34):11355-65. (PMID: 25143616)
Science. 2014 Aug 29;345(6200):1054-7. (PMID: 25170153)
Elife. 2017 Feb 21;6:. (PMID: 28220753)
Behav Neurol. 2017;2017:3435686. (PMID: 29104374)
J Neurosci. 2015 Jan 28;35(4):1763-72. (PMID: 25632149)
Nat Biomed Eng. 2021 Apr;5(4):324-345. (PMID: 33526909)
J Neurosci. 2020 Dec 2;40(49):9507-9518. (PMID: 33158958)
Behav Res Methods Instrum Comput. 2004 Aug;36(3):402-7. (PMID: 15641430)
Curr Biol. 2017 Apr 3;27(7):1074-1079. (PMID: 28343962)
J Neural Eng. 2007 Jun;4(2):120-9. (PMID: 17409486)
IEEE Trans Pattern Anal Mach Intell. 2015 May;37(5):1109-12. (PMID: 26353332)
IEEE Trans Biomed Eng. 2004 Jun;51(6):1073-6. (PMID: 15188881)

R01 NS107357 United States NS NINDS NIH HHS; R01 NS125250 United States NS NINDS NIH HHS; U01 NS113198 United States NS NINDS NIH HHS

Keywords: brain–computer interface; episodic memory; machine learning; neuromodulation

Date Created: 20230330 Date Completed: 20231011 Latest Revision: 20240331

20240331

PMC10321120

10.1093/cercor/bhad105

36997155