[en] Determining the state of consciousness in patients with disorders of consciousness is a challenging practical and theoretical problem. Recent findings suggest that multiple markers of brain activity extracted from the EEG may index the state of consciousness in the human brain. Furthermore, machine learning has been found to optimize their capacity to discriminate different states of consciousness in clinical practice. However, it is unknown how dependable these EEG markers are in the face of signal variability because of different EEG configurations, EEG protocols and subpopulations from different centres encountered in practice. In this study we analysed 327 recordings of patients with disorders of consciousness (148 unresponsive wakefulness syndrome and 179 minimally conscious state) and 66 healthy controls obtained in two independent research centres (Paris Pitié-Salpêtrière and Liège). We first show that a non-parametric classifier based on ensembles of decision trees provides robust out-of-sample performance on unseen data with a predictive area under the curve (AUC) of ~0.77 that was only marginally affected when using alternative EEG configurations (different numbers and positions of sensors, numbers of epochs, average AUC = 0.750 ± 0.014). In a second step, we observed that classifiers based on multiple as well as single EEG features generalize to recordings obtained from different patient cohorts, EEG protocols and different centres. However, the multivariate model always performed best with a predictive AUC of 0.73 for generalization from Paris 1 to Paris 2 datasets, and an AUC of 0.78 from Paris to Liège datasets. Using simulations, we subsequently demonstrate that multivariate pattern classification has a decisive performance advantage over univariate classification as the stability of EEG features decreases, as different EEG configurations are used for feature-extraction or as noise is added. Moreover, we show that the generalization performance from Paris to Liège remains stable even if up to 20% of the diagnostic labels are randomly flipped. Finally, consistent with recent literature, analysis of the learned decision rules of our classifier suggested that markers related to dynamic fluctuations in theta and alpha frequency bands carried independent information and were most influential. Our findings demonstrate that EEG markers of consciousness can be reliably, economically and automatically identified with machine learning in various clinical and acquisition contexts.
Disciplines :
Neurology
Author, co-author :
Engemann, D. A. ✱; Parietal project-team, INRIA Saclay - Île de France, France, Cognitive Neuroimaging Unit, CEA DSV/I2BM, INSERM, NeuroSpin center, Université Paris-Sud ,Université Paris-Saclay, Gif sur Yvette, France, Inserm U 1127, CNRS UMR 7225, Institut du Cerveau et de la Moelle épinière, ICM, Paris, France
King, J.-R.; Cognitive Neuroimaging Unit, CEA DSV/I2BM, INSERM, NeuroSpin center, Université Paris-Sud ,Université Paris-Saclay, Gif sur Yvette, France, New York University, 6 Washington Place, New York, NY, USA, Frankfurt Institute for Advanced Studies, Frankfurt, Germany
Rohaut, B.; Inserm U 1127, CNRS UMR 7225, Institut du Cerveau et de la Moelle épinière, ICM, Paris, France, Department of Neurology, Columbia University, New York, NY, USA
Louppe, Gilles ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data
Faugeras, F.; Inserm U 1127, CNRS UMR 7225, Institut du Cerveau et de la Moelle épinière, ICM, Paris, France
Annen, Jitka ; Université de Liège - ULiège > GIGA : Coma Group
Cassol, Helena ; Université de Liège - ULiège > GIGA : Coma Group
Fernandez-Slezak, D.; Laboratorio de Inteligencia Artificial Aplicada, Departamento de Computación FCEyN, UBA, Argentina, CONICET - Universidad de Buenos Aires, Instituto de Investigación en Ciencias de la Computación, Godoy Cruz 2290, C1425FQB, Ciudad Autónoma de Buenos Aires, Argentina
Laureys, Steven ; Université de Liège - ULiège > GIGA : Coma Group
Naccache, Lionel; Inserm U 1127, CNRS UMR 7225, Institut du Cerveau et de la Moelle épinière, ICM, Paris, France, Faculté de Médecine Pitié-Salpêtrière, Sorbonne Universités ,UPMC Université Paris 06, Paris, France
Dehaene, S.; Cognitive Neuroimaging Unit, CEA DSV/I2BM, INSERM, NeuroSpin center, Université Paris-Sud ,Université Paris-Saclay, Gif sur Yvette, France, Collège de France, Paris, France
Sitt, J. D.; Inserm U 1127, CNRS UMR 7225, Institut du Cerveau et de la Moelle épinière, ICM, Paris, France, Faculté de Médecine Pitié-Salpêtrière, Sorbonne Universités ,UPMC Université Paris 06, Paris, France
Axmacher N, Henseler MM, Jensen O, Weinreich I, Elger CE, Fell J. Cross-frequency coupling supports multi-item working memory in the human hippocampus. Proc Natl Acad Sci USA 2010; 107: 3228-33.
Bayne T, Hohwy J, Owen AM. Are there levels of consciousness?. Trends Cogn Sci 2016; 20: 405-13.
Bekinschtein TA, Dehaene S, Rohaut B, Tadel F, Cohen L, Naccache L. Neural signature of the conscious processing of auditory regularities. Proc Natl Acad Sci USA 2009; 106: 1672-7.
Bruno MA, Vanhaudenhuyse A, Thibaut A, Moonen G, Laureys S. From unresponsive wakefulness to minimally conscious PLUS and functional locked-in syndromes: Recent advances in our understanding of disorders of consciousness. J Neurol 2011; 258: 1373-84.
Bzdok D, Engemann D-A, Grisel O, Varoquaux G, Thirion B. Prediction and inference diverge in biomedicine: Simulations and real-world data. bioRxiv 2018. doi: 10.1101/327437.
Casali AG, Gosseries O, Rosanova M, Boly M, Sarasso S, Casali KR, et al. A theoretically based index of consciousness independent of sensory processing and behavior. Sci Transl Med 2013; 5: 198ra105.
Chang HY, Nuyten DSA, Sneddon JB, Hastie T, Tibshirani R, Sørlie T, et al. Robustness, scalability, and integration of a wound-response gene expression signature in predicting breast cancer survival. Proc Natl Acad Sci USA 2005; 102: 3738-43.
Chennu S, Annen J, Wannez S, Thibaut A, Chatelle C, Cassol H, et al. Brain networks predict metabolism, diagnosis and prognosis at the bedside in disorders of consciousness. Brain 2017; 140: 2120-32.
Claassen J, Velazquez A, Meyers E, Witsch J, Falo MC, Park S, et al. Bedside quantitative electroencephalography improves assessment of consciousness in comatose subarachnoid hemorrhage patients. Ann Neurol 2016; 80: 541-53.
Cruse D, Chennu S, Chatelle C, Bekinschtein TA, Fernández-Espejo D, Pickard JD, et al. Bedside detection of awareness in the vegetative state: A cohort study. Lancet 2012; 378: 2088-94.
Curley WH, Forgacs PB, Voss HU, Conte MM, Schiff ND. Characterization of EEG signals revealing covert cognition in the injured brain. Brain 2018; 141: 1404-21.
Dehaene S, Changeux J-P, Naccache L, Sackur J, Sergent C. Conscious, preconscious, and subliminal processing: A testable taxonomy. Trends Cogn Sci 2006; 10: 204-11.
Dehaene S, Naccache L. Towards a cognitive neuroscience of consciousness: Basic evidence and a workspace framework. Cognition 2001; 79: 1-37.
Demertzi A, Antonopoulos G, Heine L, Voss HU, Crone JS, De Los Angeles C, et al. Intrinsic functional connectivity differentiates minimally conscious from unresponsive patients. Brain 2015; 138: 2619-31.
Demertzi A, Gomez F, Crone JS, Vanhaudenhuyse A, Tshibanda L, Noirhomme Q, et al. Multiple fMRI system-level baseline connectivity is disrupted in patients with consciousness alterations. Cortex 2014; 52: 35-46.
Donchin E, Coles MGH. Is the P300 component a manifestation of context updating. Behav Brain Sci 1988; 11: 357-427.
Efron B, Tibshirani R. An introduction to the bootstrap New York, NY: Chapman & Hall; 1993.
Emmons WH, Simon CW. EEG, consciousness, and sleep. Science 1956; 124: 1066-9.
Engemann D, Raimondo F, King J-R, Jas M, Gramfort A, Dehaene S, et al. Automated measurement and prediction of consciousness in vegetative and minimally conscious patients. In: ICML workshop on statistics, machine learning and neuroscience 2015. Lille, France; 2015.
Faugeras F, Rohaut B, Valente M, Sitt J, Demeret S, Bolgert F, et al. Survival and consciousness recovery are better in the minimally conscious state than in the vegetative state. Brain Inj 2018; 32: 72-7.
Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Machine Learning 2006; 63: 3. Springer/Kluwer Academic Publishers.
Giacino JT, Ashwal S, Childs N, Cranford R, Jennett B, Katz DI, et al. The minimally conscious state definition and diagnostic criteria. Neurology 2002; 58: 349-53.
Giacino JT, Kalmar K, Whyte J. The JFK Coma Recovery Scale- Revised: Measurement characteristics and diagnostic utility11No commercial party having a direct financial interest in the results of the research supporting this article has or will confer a benefit upon the authors or upon. Arch Phys Med Rehabil 2004; 85: 2020-9.
Goldfine AM, Victor JD, Conte MM, Bardin JC, Schiff ND. Determination of awareness in patients with severe brain injury using EEG power spectral analysis. Clin Neurophysiol 2011; 122: 2157-68.
Gosseries O, Zasler ND, Laureys S. Recent advances in disorders of consciousness: Focus on the diagnosis. Brain Inj 2014; 28: 1141-50.
Gramfort A, Luessi M, Larson E, Engemann D, Strohmeier D, Brodbeck C, et al. MNE software for processing MEG and EEG data. Neuroimage 2014; 86: 446-60.
Iotzov I, Fidali BC, Petroni A, Conte MM, Schiff ND, Parra LC. Divergent neural responses to narrative speech in disorders of consciousness. Ann Clin Transl Neurol 2017; 4: 784-92.
Jas M, Engemann DA, Bekhti Y, Raimondo F, Gramfort A. Autoreject: Automated artifact rejection for MEG and EEG data. Neuroimage 2017; 159: 417-29.
Jennett B, Plum F. Persistent vegetative state after brain damage: A syndrome in search of a name. Lancet 1972; 299: 734-7.
King J-R, Sitt JD, Faugeras F, Rohaut B, Karoui I El, Cohen L, et al. Information sharing in the brain indexes consciousness in noncommunicative patients. Curr Biol 2013a; 23: 1914-19.
King JR, Faugeras F, Gramfort A, Schurger A, El Karoui I, Sitt JD, et al. Single-trial decoding of auditory novelty responses facilitates the detection of residual consciousness. Neuroimage 2013b; 83: 726-38.
Laureys S, Celesia GG, Cohadon F, Lavrijsen J, JoséL-C, Sannita WG, et al. Unresponsive wakefulness syndrome: A new name for the vegetative state or apallic syndrome. BMC Med 2010; 8: 68.
Lo A, Chernoff H, Zheng T, Lo S-H. Why significant variables aren't automatically good predictors. Pro. Natl Acad Sci USA 2015; 112: 13892-7.
Louppe G, Wehenkel L, Sutera A, Geurts P. Understanding variable importances in forests of randomized trees. In: Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ, editors. Advances in neural information processing systems 26 (NIPS). Lake Tahoe: Curran Associates, Inc., 2013; p. 431-439.
Louppe G. Understanding random forests: From theory to practice. PhD thesis. University of Liège, Faculty of Applied Sciences, Department of Electrical Engineering & Computer Science, 2014.
LuautéJ, Maucort-Boulch D, Tell L, Quelard F, Sarraf T, Iwaz J, et al. Long-term outcomes of chronic minimally conscious and vegetative states. Neurology 2010; 75: 246-52.
LuléD, Noirhomme Q, Kleih SC, Chatelle C, Halder S, Demertzi A, et al. Probing command following in patients with disorders of consciousness using a brain-computer interface. Clin Neurophysiol 2013; 124: 101-6.
Monti MM, Vanhaudenhuyse A, Coleman MR, Boly M, Pickard JD, Tshibanda L, et al. Willful modulation of brain activity in disorders of consciousness. N Engl J.Med 2010; 362: 579-89.
Naccache L. Minimally conscious state or cortically mediated state?. Brain 2018; 141: 949-60.
Naci L, Monti MM, Cruse D, Kübler A, Sorger B, Goebel R, et al. Brain-computer interfaces for communication with nonresponsive patients. Ann Neurol 2012; 72: 312-23.
Owen AM, Coleman MR, Boly M, Davis MH, Laureys S, Pickard JD. Detecting awareness in the vegetative state. Science 2006; 313: 1402.
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in python. J Mach Learn Res 2011; 12: 2825-30.
Phillips CL, Bruno M-A, Maquet P, Boly M, Noirhomme Q, Schnakers C, et al. "Relevance vector machine'' consciousness classifier applied to cerebral metabolism of vegetative and locked-in patients. Neuroimage 2011; 56: 797-808.
Pins D. The neural correlates of conscious vision. Cereb Cortex 2003; 13: 461-74.
Polich J. Updating P300: An integrative theory of P3a and P3b. Clin Neurophysiol 2007; 118: 2128-48.
Purdon PL, Pierce ET, Mukamel EA, Prerau MJ, Walsh JL, Wong KFK, et al. Electroencephalogram signatures of loss and recovery of consciousness from propofol. Proc Natl Acad Sci USA 2013; 110: E1142-51.
Rohaut B, Claassen J. Decision making in perceived devastating brain injury: A call to explore the impact of cognitive biases. Br J Anaesth 2018; 120: 5-9.
Rohaut B, Raimondo F, Galanaud D, Valente M, Sitt JD, Naccache L. Probing consciousness in a sensory-disconnected paralyzed patient. Brain Inj 2017; 31: 1398-403.
Rosenberg GA, Johnson SF, Brenner RP. Recovery of cognition after prolonged vegetative state. Ann Neurol 1977; 2: 167-8.
Sadaghiani S, Kleinschmidt A. Brain networks and/-oscillations: Structural and functional foundations of cognitive control. Trends Cogn Sci 2016; 20: 805-17.
Saeb S, Lonini L, Jayaraman A, Mohr DC, Kording KP. The need to approximate the use-case in clinical machine learning. Gigascience 2017; 6: 1-9.
Schiff ND. Recovery of consciousness after brain injury: A mesocircuit hypothesis. Trends Neurosci 2010; 33: 1-9.
Schiff ND. Cognitive motor dissociation following severe brain injuries. JAMA Neurol 2015; 72: 1413-15.
Schiff ND, Nauvel T, Victor JD. Large-scale brain dynamics in disorders of consciousness. Curr Opin Neurobiol 2014; 25: 7-14.
Schnakers C, Vanhaudenhuyse A, Giacino J, Ventura M, Boly M, Majerus S, et al. Diagnostic accuracy of the vegetative and minimally conscious state: Clinical consensus versus standardized neurobehavioral assessment. BMC Neurol 2009; 9: 35.
Sergent C, Baillet S, Dehaene S. Timing of the brain events underlying access to consciousness during the attentional blink. Nat Neurosci 2005; 8: 1391-400.
Sergent C, Faugeras F, Rohaut B, Perrin F, Valente M, Tallon-Baudry C, et al. Multidimensional cognitive evaluation of patients with disorders of consciousness using EEG: A proof of concept study. Neuroimage Clin 2017; 13: 455-69.
Sitt JD, King J-R, El Karoui I, Rohaut B, Faugeras F, Gramfort A, et al. Large scale screening of neural signatures of consciousness in patients in a vegetative or minimally conscious state. Brain 2014; 137: 2258-70.
Stender J, Gosseries O, Bruno M-A, Charland-Verville V, Vanhaudenhuyse A, Demertzi A, et al. Diagnostic precision of PET imaging and functional MRI in disorders of consciousness: A clinical validation study. Lancet 2014; 384: 514-22.
Varoquaux G. Cross-validation failure: Small sample sizes lead to large error bars. Neuroimage 2018; 180: 68-77.
Varoquaux G, Raamana PR, Engemann DA, Hoyos-Idrobo A, Schwartz Y, Thirion B. Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines. Neuroimage 2016
Victor JD, Drover JD, Conte MM, Schiff ND. Mean-field modeling of thalamocortical dynamics and a model-driven approach to EEG analysis. Proc Natl Acad Sci USA 2011; 108 (Suppl 3): 15631-8.
Wannez S, Heine L, Thonnard M, Gosseries O, Laureys S; Coma Science Group Collaborators. The repetition of behavioral assessments in diagnosis of disorders of consciousness. Ann Neurol 2017; 81: 883-9.
Williams ST, Conte MM, Goldfine AM, Noirhomme Q, Gosseries O, Thonnard M, et al. Common resting brain dynamics indicate a possible mechanism underlying zolpidem response in severe brain injury. Elife 2013; 2: E01157.