Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning.
Journal
Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555
Informations de publication
Date de publication:
25 02 2022
25 02 2022
Historique:
received:
08
08
2020
accepted:
25
01
2022
entrez:
26
2
2022
pubmed:
27
2
2022
medline:
13
4
2022
Statut:
epublish
Résumé
Consciousness can be defined by two components: arousal (wakefulness) and awareness (subjective experience). However, neurophysiological consciousness metrics able to disentangle between these components have not been reported. Here, we propose an explainable consciousness indicator (ECI) using deep learning to disentangle the components of consciousness. We employ electroencephalographic (EEG) responses to transcranial magnetic stimulation under various conditions, including sleep (n = 6), general anesthesia (n = 16), and severe brain injury (n = 34). We also test our framework using resting-state EEG under general anesthesia (n = 15) and severe brain injury (n = 34). ECI simultaneously quantifies arousal and awareness under physiological, pharmacological, and pathological conditions. Particularly, ketamine-induced anesthesia and rapid eye movement sleep with low arousal and high awareness are clearly distinguished from other states. In addition, parietal regions appear most relevant for quantifying arousal and awareness. This indicator provides insights into the neural correlates of altered states of consciousness.
Identifiants
pubmed: 35217645
doi: 10.1038/s41467-022-28451-0
pii: 10.1038/s41467-022-28451-0
pmc: PMC8881479
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1064Subventions
Organisme : NIMH NIH HHS
ID : R01 MH064498
Pays : United States
Informations de copyright
© 2022. The Author(s).
Références
Sanders, R. D., Tononi, G., Laureys, S. & Sleigh, J. W. Unresponsiveness unconsciousness. Anesthesiology 116, 946–959 (2012).
pubmed: 22314293
doi: 10.1097/ALN.0b013e318249d0a7
Darracq, M. et al. Evoked alpha power is reduced in disconnected consciousness during sleep and anesthesia. Sci. Rep. 8, 16664 (2018).
pubmed: 30413741
pmcid: 6226534
doi: 10.1038/s41598-018-34957-9
Colombo, M. A. et al. The spectral exponent of the resting EEG indexes the presence of consciousness during unresponsiveness induced by propofol, xenon, and ketamine. Neuroimage 189, 631–644 (2019).
pubmed: 30639334
doi: 10.1016/j.neuroimage.2019.01.024
Lendner, J. D. et al. An electrophysiological marker of arousal level in humans. eLife 9, e55092 (2020).
pubmed: 32720644
pmcid: 7394547
doi: 10.7554/eLife.55092
Mashour, G. A. & Hudetz, A. G. Neural correlates of unconsciousness in large-scale brain networks. Trends Neurosci. 41, 150–160 (2018).
pubmed: 29409683
pmcid: 5835202
doi: 10.1016/j.tins.2018.01.003
Casarotto, S. et al. Exploring the neurophysiological correlates of loss and recovery of consciousness: perturbational complexity in Brain Function and Responsiveness in Disorders of Consciousness (ed Monti, M. M.) 93–104 (Springer, 2016).
Bonhomme, V. et al. General anesthesia: a probe to explore consciousness. Front. Syst. Neurosci. 13, 36 (2019).
pubmed: 31474839
pmcid: 6703193
doi: 10.3389/fnsys.2019.00036
Sanders, R. D. et al. Incidence of connected consciousness after tracheal intubation: a prospective, international, multicenter cohort study of the isolated forearm technique. Anesthesiology 126, 214–222 (2017).
pubmed: 27984262
doi: 10.1097/ALN.0000000000001479
Noirhomme, Q., Brecheisen, R., Lesenfants, D., Antonopoulos, G. & Laureys, S. “Look at my classifier’s result”: disentangling unresponsive from (minimally) conscious patients. Neuroimage 145, 288–303 (2017).
pubmed: 26690804
doi: 10.1016/j.neuroimage.2015.12.006
Giacino, J. T. et al. The minimally conscious state: definition and diagnostic criteria. J. Neurol. 58, 349–353 (2002).
Gosseries, O., Di, H., Laureys, S. & Boly, M. Measuring consciousness in severely damaged brains. Annu. Rev. Neurosci. 37, 457–478 (2014).
pubmed: 25002279
doi: 10.1146/annurev-neuro-062012-170339
Giacino, J. T., Kalmar, K. & Whyte, J. The JFK Coma Recovery Scale-Revised: measurement characteristics and diagnostic utility. Arch. Phys. Med. Rehabil. 85, 2020–2029 (2004).
pubmed: 15605342
doi: 10.1016/j.apmr.2004.02.033
Thibaut, A. et al. Preservation of Brain Activity in Unresponsive Patients Identifies MCS Star. Ann Neurol 90, 89–100 https://doi.org/10.1002/ana.26095 (2021).
Gosseries, O., Zasler, N. D. & Laureys, S. Recent advances in disorders of consciousness: focus on the diagnosis. Brain Inj. 28, 1141–1150 (2014).
pubmed: 25099018
doi: 10.3109/02699052.2014.920522
Stender, J. et al. Diagnostic precision of PET imaging and functional MRI in disorders of consciousness: a clinical validation study. Lancet 384, 514–522 (2014).
pubmed: 24746174
doi: 10.1016/S0140-6736(14)60042-8
Casali, A. G. et al. A theoretically based index of consciousness independent of sensory processing and behavior. Sci. Transl. Med. 5, 198ra105–198ra105 (2013).
pubmed: 23946194
doi: 10.1126/scitranslmed.3006294
Casarotto, S. et al. Stratification of unresponsive patients by an independently validated index of brain complexity. Ann. Neurol. 80, 718–729 (2016).
pubmed: 27717082
pmcid: 5132045
doi: 10.1002/ana.24779
Gosseries, O. et al. Automated EEG entropy measurements in coma, vegetative state/unresponsive wakefulness syndrome and minimally conscious state. Funct. Neurol. 26, 25 (2011).
pubmed: 21693085
pmcid: 3814509
Engemann, D. A. et al. Robust EEG-based cross-site and cross-protocol classification of states of consciousness. Brain 141, 3179–3192 (2018).
pubmed: 30285102
doi: 10.1093/brain/awy251
Baird, B. et al. Human rapid eye movement sleep shows local increases in low-frequency oscillations and global decreases in high-frequency oscillations compared to resting wakefulness. eNeuro 5, 4 (2018).
doi: 10.1523/ENEURO.0293-18.2018
Müller, K.-R. et al. Machine learning for real-time single-trial EEG-analysis: from brain–computer interfacing to mental state monitoring. J. Neurosci. Methods 167, 82–90 (2008).
pubmed: 18031824
doi: 10.1016/j.jneumeth.2007.09.022
Lemm, S., Blankertz, B., Dickhaus, T. & Müller, K.-R. Introduction to machine learning for brain imaging. Neuroimage 56, 387–399 (2011).
pubmed: 21172442
doi: 10.1016/j.neuroimage.2010.11.004
Liu, Q. et al. Spectrum analysis of EEG signals using CNN to model patient’s consciousness level based on anesthesiologists’ experience. IEEE Access 7, 53731–53742 (2019).
doi: 10.1109/ACCESS.2019.2912273
Fahimi, F. et al. Inter-subject transfer learning with end-to-end deep convolutional neural network for EEG-based BCI. J. Neural Eng. 16, 026007 (2019).
pubmed: 30524056
doi: 10.1088/1741-2552/aaf3f6
Webb, S. Deep learning for biology. Nature 554, 555–557 (2018).
Montavon, G., Binder, A., Lapuschkin, S., Samek, W. & Müller, K.-R. Layer-wise relevance propagation: an overview in explainable AI: interpreting, explaining and visualizing deep learning (eds Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., Müller, K.-R.) 193–209 (Springer, 2019).
Kwon, O.-Y., Lee, M.-H., Guan, C. & Lee, S.-W. Subject-independent brain-computer interfaces based on deep convolutional neural networks. IEEE Trans. Neural Netw. Learn. Syst. 31, 3839–3852 (2020).
pubmed: 31725394
doi: 10.1109/TNNLS.2019.2946869
Sturm, I., Lapuschkin, S., Samek, W. & Müller, K.-R. Interpretable deep neural networks for single-trial EEG classification. J. Neurosci. Methods 274, 141–145 (2016).
pubmed: 27746229
doi: 10.1016/j.jneumeth.2016.10.008
Lotte, F. et al. A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J. Neural Eng. 15, 031005 (2018).
pubmed: 29488902
doi: 10.1088/1741-2552/aab2f2
Lapuschkin, S., Binder, A., Montavon, G., Müller, K.-R. & Samek, W. The LRP toolbox for artificial neural networks. J. Mach. Learn. Res. 17, 3938–3942 (2016).
Massimini, M. et al. Triggering sleep slow waves by transcranial magnetic stimulation. Proc. Natl. Acad. Sci. USA 104, 8496–8501 (2007).
pubmed: 17483481
pmcid: 1895978
doi: 10.1073/pnas.0702495104
Massimini, M., Tononi, G. & Huber, R. Slow waves, synaptic plasticity and information processing: insights from transcranial magnetic stimulation and high-density EEG experiments. Eur. J. Neurosci. 29, 1761–1770 (2009).
pubmed: 19473231
doi: 10.1111/j.1460-9568.2009.06720.x
Napolitani, M. et al. Transcranial magnetic stimulation combined with high-density EEG in altered states of consciousness. Brain Inj. 28, 1180–1189 (2014).
pubmed: 25099022
doi: 10.3109/02699052.2014.920524
Massimini, M. et al. Breakdown of cortical effective connectivity during sleep. Science 309, 2228–2232 (2005).
pubmed: 16195466
doi: 10.1126/science.1117256
Rosanova, M. et al. Recovery of cortical effective connectivity and recovery of consciousness in vegetative patients. Brain 135, 1308–1320 (2012).
pubmed: 22226806
pmcid: 3326248
doi: 10.1093/brain/awr340
Sarasso, S. et al. Consciousness and complexity during unresponsiveness induced by propofol, xenon, and ketamine. Curr. Biol. 25, 3099–3105 (2015).
pubmed: 26752078
doi: 10.1016/j.cub.2015.10.014
Luppi, A. I. et al. Consciousness-specific dynamic interactions of brain integration and functional diversity. Nat. Commun. 10, 4616 (2019).
pubmed: 31601811
pmcid: 6787094
doi: 10.1038/s41467-019-12658-9
Jeon, E., Ko, W. & Suk, H.-I. Domain adaptation with source selection for motor-imagery based BCI. in 2019 7th International Winter Conference on Brain-Computer Interface (BCI). 1–4 (IEEE).
Lawhern, V. J. et al. EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J. Neural Eng. 15, 056013 (2018).
pubmed: 29932424
doi: 10.1088/1741-2552/aace8c
Koch, C., Massimini, M., Boly, M. & Tononi, G. Posterior and anterior cortex—where is the difference that makes the difference? Nat. Rev. Neurosci. 17, 666 (2016).
pubmed: 27466141
doi: 10.1038/nrn.2016.105
Siclari, F. & Tononi, G. Local aspects of sleep and wakefulness. Curr. Opin. Neurobiol. 44, 222–227 (2017).
pubmed: 28575720
pmcid: 6445546
doi: 10.1016/j.conb.2017.05.008
Siclari, F., Bernardi, G., Cataldi, J. & Tononi, G. Dreaming in NREM sleep: a high-density EEG study of slow waves and spindles. J. Neurosci. 38, 9175–9185 (2018).
pubmed: 30201768
pmcid: 6199409
doi: 10.1523/JNEUROSCI.0855-18.2018
Nieminen, J. O. et al. Consciousness and cortical responsiveness: a within-state study during non-rapid eye movement sleep. Sci. Rep. 6, 30932 (2016).
pubmed: 27491799
pmcid: 4974655
doi: 10.1038/srep30932
Lee, M. et al. Connectivity differences between consciousness and unconsciousness in non-rapid eye movement sleep: a TMS–EEG study. Sci. Rep. 9, 5175 (2019).
pubmed: 30914674
pmcid: 6435892
doi: 10.1038/s41598-019-41274-2
Lee, M. et al. Network properties in transitions of consciousness during propofol-induced sedation. Sci. Rep. 7, 16791 (2017).
pubmed: 29196672
pmcid: 5711919
doi: 10.1038/s41598-017-15082-5
Chennu, S. et al. Brain networks predict metabolism, diagnosis and prognosis at the bedside in disorders of consciousness. Brain 140, 2120–2132 (2017).
pubmed: 28666351
doi: 10.1093/brain/awx163
Afrasiabi, M. et al. Consciousness depends on integration between parietal cortex, striatum, and thalamus. Cell Syst. 12, 363–373 (2021).
Vanhaudenhuyse, A. et al. Default network connectivity reflects the level of consciousness in non-communicative brain-damaged patients. Brain 133, 161–171 (2010).
pubmed: 20034928
doi: 10.1093/brain/awp313
Andersen, L. M., Pedersen, M. N., Sandberg, K. & Overgaard, M. Occipital MEG activity in the early time range (<300 ms) predicts graded changes in perceptual consciousness. Cereb. Cortex 26, 2677–2688 (2016).
pubmed: 26009612
doi: 10.1093/cercor/bhv108
Russo, S. et al. TAAC–TMS Adaptable Auditory Control: a universal tool to mask TMS clicks. J. Neurosci. Meth., https://doi.org/10.1016/j.jneumeth.2022.109491 (2022).
Casarotto, S. et al. The rt-TEP tool: real-time visualization of TMS-evoked potentials to maximize cortical activation and minimize artifacts. J. Neurosci. Meth. 370, 109486 (2022).
Belardinelli, P. et al. Reproducibility in TMS–EEG studies: a call for data sharing, standard procedures and effective experimental control. Brain Stimul. 12, 787–790 (2019).
pubmed: 30738777
doi: 10.1016/j.brs.2019.01.010
Lee, M. et al. Graph theoretical analysis of cortical networks based on conscious experience. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 3373–3376 (IEEE).
Bodart, O. et al. Measures of metabolism and complexity in the brain of patients with disorders of consciousness. Neuroimage Clin. 14, 354–362 (2017).
pubmed: 28239544
pmcid: 5318348
doi: 10.1016/j.nicl.2017.02.002
Bodart, O. et al. Global structural integrity and effective connectivity in patients with disorders of consciousness. Brain Stimul. 11, 358–365 (2018).
pubmed: 29162503
doi: 10.1016/j.brs.2017.11.006
Rosanova, M. et al. Sleep-like cortical OFF-periods disrupt causality and complexity in the brain of unresponsive wakefulness syndrome patients. Nat. Commun. 9, 4427 (2018).
pubmed: 30356042
pmcid: 6200777
doi: 10.1038/s41467-018-06871-1
Delorme, A. & Makeig, S. EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J. Neurosci. Methods 134, 9–21 (2004).
pubmed: 15102499
doi: 10.1016/j.jneumeth.2003.10.009
Bertrand, O., Perrin, F. & Pernier, J. A theoretical justification of the average reference in topographic evoked potential studies. Electroencephalogr. Clin. Neurophysiol. 62, 462–464 (1985).
pubmed: 2415344
doi: 10.1016/0168-5597(85)90058-9
Ludwig, K. A. et al. Using a common average reference to improve cortical neuron recordings from microelectrode arrays. J. Neurophysiol. 101, 1679–1689 (2009).
pubmed: 19109453
doi: 10.1152/jn.90989.2008
Zhang, D. et al. Cascade and parallel convolutional recurrent neural networks on EEG-based intention recognition for brain computer interface. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 1703–1710.
Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Preprint at arXiv https://arxiv.org/abs/1412.6980 (2014).
Blankertz, B., Lemm, S., Treder, M., Haufe, S. & Müller, K.-R. Single-trial analysis and classification of ERP components—a tutorial. Neuroimage 56, 814–825 (2011).
pubmed: 20600976
doi: 10.1016/j.neuroimage.2010.06.048
Smits, G. F. & Jordaan, E. M. Improved SVM regression using mixtures of kernels. in 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No. 02CH37290). 2785–2790 (IEEE).
Rueda-Delgado, L. et al. Brain event-related potentials predict individual differences in inhibitory control. Int. J. Psychophysiol. 18, 30870–30875 (2019).
Korjus, K., Hebart, M. N. & Vicente, R. An efficient data partitioning to improve classification performance while keeping parameters interpretable. PLoS ONE 11, e0161788 (2016).
pubmed: 27564393
pmcid: 5001642
doi: 10.1371/journal.pone.0161788
Thiery, T. et al. Long-range temporal correlations in the brain distinguish conscious wakefulness from induced unconsciousness. Neuroimage 179, 30–39 (2018).
pubmed: 29885482
doi: 10.1016/j.neuroimage.2018.05.069
Krepki, R., Blankertz, B., Curio, G. & Müller, K.-R. The Berlin Brain-Computer Interface (BBCI)—towards a new communication channel for online control in gaming applications. Multimed. Tools Appl. 33, 73–90 (2007).
doi: 10.1007/s11042-006-0094-3
Lapuschkin, S. et al. Unmasking Clever Hans predictors and assessing what machines really learn. Nat. Commun. 10, 1096 (2019).
pubmed: 30858366
pmcid: 6411769
doi: 10.1038/s41467-019-08987-4
Tóth, B. et al. EEG network connectivity changes in mild cognitive impairment—preliminary results. Int. J. Psychophysiol. 92, 1–7 (2014).
pubmed: 24508504
doi: 10.1016/j.ijpsycho.2014.02.001
Nir, Y., Massimini, M., Boly, M. & Tononi, G. Sleep and consciousness in Sleep and Consciousness (ed Cavanna, A. E., Nani, A., Blumenfeld, H. & Laureys, S.) Chapter 9, 133–182 (Springer Berlin Heidelberg, 2013).
Lee, M. et al. Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning. MinjiLee-ku/ECI: First release of ECI_update. https://doi.org/10.5281/zenodo.5760787 (2021).