Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning

Minji Lee; Leandro R.D. Sanz; Alice Barra; Audrey Wolff; Jaakko O. Nieminen; Melanie Boly; Mario Rosanova; Silvia Casarotto; Olivier Bodart; Jitka Annen; Aurore Thibaut; Rajanikant Panda; Vincent Bonhomme; Marcello Massimini; Giulio Tononi; Steven Laureys; Olivia Gosseries; Seong Whan Lee

doi:10.1038/s41467-022-28451-0

Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning

Minji Lee, Leandro R.D. Sanz, Alice Barra, Audrey Wolff, Jaakko O. Nieminen, Melanie Boly, Mario Rosanova, Silvia Casarotto, Olivier Bodart, Jitka Annen, Aurore Thibaut, Rajanikant Panda, Vincent Bonhomme, Marcello Massimini, Giulio Tononi, Steven Laureys, Olivia Gosseries, Seong Whan Lee

Biomedical software Engineering

Research output: Contribution to journal › Article › peer-review

48 Scopus citations

Abstract

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.

Original language	English
Article number	1064
Journal	Nature Communications
Volume	13
Issue number	1
DOIs	https://doi.org/10.1038/s41467-022-28451-0
State	Published - Dec 2022

Bibliographical note

Funding Information:
This work was supported by the Institute for Information and Communications Technology Planning and Evaluation (IITP) funded by the Korean government (Nos. 2017-0-00451; 2017-0-01779; 2019-0-00079; 2019-0-01371; and 2021-0-02068), the University and University Hospital of Liège, Belgian National Fund for Scientific Research (F.R.S-FNRS), the Italian Ministry of Health, GR-2016–02361494 (to S.C.), the Canadian Institute for Advanced Research (CIFAR) (to M.M.), European Union’s Horizon 2020 Framework Program for Research and Innovation under the Specific Grant Agreement (No. 945539, Human Brain Project SGA3) (to M.M. and S.L.), BIAL Foundation, AstraZeneca Foundation, Fund Generate, King Baudouin Foundation, DOCMA project [EU-H2020-MSCA-RISE-–778234], James McDonnell Foundation, Mind Science Foundation, Fondazione Europea di Ricerca Biomedica, National Institutes of Health (No. R01MH064498), Academy of Finland (Nos. 265680 and 294625), Tiny Blue Dot Foundation (to M.M.), and grant EraPerMed JTC 2019 “PerBrain” (to M.R.). L.R.D.S. and R.P. are PhD fellows, O.G. and A. T. are research associates, and S.L. is research director at the F.R.S.–FNRS. We thank S. Lapuschkin for sharing the code; further, we thank all the healthy participants, patients, and their families who participated in this study.

Publisher Copyright:
© 2022, The Author(s).

Access to Document

10.1038/s41467-022-28451-0

Cite this

Lee, M., Sanz, L. R. D., Barra, A., Wolff, A., Nieminen, J. O., Boly, M., Rosanova, M., Casarotto, S., Bodart, O., Annen, J., Thibaut, A., Panda, R., Bonhomme, V., Massimini, M., Tononi, G., Laureys, S., Gosseries, O., & Lee, S. W. (2022). Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning. Nature Communications, 13(1), Article 1064. https://doi.org/10.1038/s41467-022-28451-0

@article{5e974001122a4dc1a6f867193bddbb68,

title = "Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning",

abstract = "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.",

author = "Minji Lee and Sanz, {Leandro R.D.} and Alice Barra and Audrey Wolff and Nieminen, {Jaakko O.} and Melanie Boly and Mario Rosanova and Silvia Casarotto and Olivier Bodart and Jitka Annen and Aurore Thibaut and Rajanikant Panda and Vincent Bonhomme and Marcello Massimini and Giulio Tononi and Steven Laureys and Olivia Gosseries and Lee, {Seong Whan}",

note = "Funding Information: This work was supported by the Institute for Information and Communications Technology Planning and Evaluation (IITP) funded by the Korean government (Nos. 2017-0-00451; 2017-0-01779; 2019-0-00079; 2019-0-01371; and 2021-0-02068), the University and University Hospital of Li{\`e}ge, Belgian National Fund for Scientific Research (F.R.S-FNRS), the Italian Ministry of Health, GR-2016–02361494 (to S.C.), the Canadian Institute for Advanced Research (CIFAR) (to M.M.), European Union{\textquoteright}s Horizon 2020 Framework Program for Research and Innovation under the Specific Grant Agreement (No. 945539, Human Brain Project SGA3) (to M.M. and S.L.), BIAL Foundation, AstraZeneca Foundation, Fund Generate, King Baudouin Foundation, DOCMA project [EU-H2020-MSCA-RISE-–778234], James McDonnell Foundation, Mind Science Foundation, Fondazione Europea di Ricerca Biomedica, National Institutes of Health (No. R01MH064498), Academy of Finland (Nos. 265680 and 294625), Tiny Blue Dot Foundation (to M.M.), and grant EraPerMed JTC 2019 “PerBrain” (to M.R.). L.R.D.S. and R.P. are PhD fellows, O.G. and A. T. are research associates, and S.L. is research director at the F.R.S.–FNRS. We thank S. Lapuschkin for sharing the code; further, we thank all the healthy participants, patients, and their families who participated in this study. Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1038/s41467-022-28451-0",

language = "English",

volume = "13",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

Lee, M, Sanz, LRD, Barra, A, Wolff, A, Nieminen, JO, Boly, M, Rosanova, M, Casarotto, S, Bodart, O, Annen, J, Thibaut, A, Panda, R, Bonhomme, V, Massimini, M, Tononi, G, Laureys, S, Gosseries, O & Lee, SW 2022, 'Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning', Nature Communications, vol. 13, no. 1, 1064. https://doi.org/10.1038/s41467-022-28451-0

TY - JOUR

T1 - Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning

AU - Lee, Minji

AU - Sanz, Leandro R.D.

AU - Barra, Alice

AU - Wolff, Audrey

AU - Nieminen, Jaakko O.

AU - Boly, Melanie

AU - Rosanova, Mario

AU - Casarotto, Silvia

AU - Bodart, Olivier

AU - Annen, Jitka

AU - Thibaut, Aurore

AU - Panda, Rajanikant

AU - Bonhomme, Vincent

AU - Massimini, Marcello

AU - Tononi, Giulio

AU - Laureys, Steven

AU - Gosseries, Olivia

AU - Lee, Seong Whan

N1 - Funding Information: This work was supported by the Institute for Information and Communications Technology Planning and Evaluation (IITP) funded by the Korean government (Nos. 2017-0-00451; 2017-0-01779; 2019-0-00079; 2019-0-01371; and 2021-0-02068), the University and University Hospital of Liège, Belgian National Fund for Scientific Research (F.R.S-FNRS), the Italian Ministry of Health, GR-2016–02361494 (to S.C.), the Canadian Institute for Advanced Research (CIFAR) (to M.M.), European Union’s Horizon 2020 Framework Program for Research and Innovation under the Specific Grant Agreement (No. 945539, Human Brain Project SGA3) (to M.M. and S.L.), BIAL Foundation, AstraZeneca Foundation, Fund Generate, King Baudouin Foundation, DOCMA project [EU-H2020-MSCA-RISE-–778234], James McDonnell Foundation, Mind Science Foundation, Fondazione Europea di Ricerca Biomedica, National Institutes of Health (No. R01MH064498), Academy of Finland (Nos. 265680 and 294625), Tiny Blue Dot Foundation (to M.M.), and grant EraPerMed JTC 2019 “PerBrain” (to M.R.). L.R.D.S. and R.P. are PhD fellows, O.G. and A. T. are research associates, and S.L. is research director at the F.R.S.–FNRS. We thank S. Lapuschkin for sharing the code; further, we thank all the healthy participants, patients, and their families who participated in this study. Publisher Copyright: © 2022, The Author(s).

PY - 2022/12

Y1 - 2022/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85125515933&partnerID=8YFLogxK

U2 - 10.1038/s41467-022-28451-0

DO - 10.1038/s41467-022-28451-0

M3 - Article

C2 - 35217645

AN - SCOPUS:85125515933

SN - 2041-1723

VL - 13

JO - Nature Communications

JF - Nature Communications

IS - 1

M1 - 1064

ER -

Quantifying arousal and awareness in altered states of consciousness using interpretable deep learning

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this