Frontal electroencephalogram based drug, sex, and age independent sedation level prediction using non-linear machine learning algorithms
S M Ramaswamy, M H Kuizenga, M A S Weerink, H E M Vereecke, M M R F Struys, S Belur Nagaraj, S M Ramaswamy, M H Kuizenga, M A S Weerink, H E M Vereecke, M M R F Struys, S Belur Nagaraj
Abstract
Brain monitors which track quantitative electroencephalogram (EEG) signatures to monitor sedation levels are drug and patient specific. There is a need for robust sedation level monitoring systems to accurately track sedation levels across all drug classes, sex and age groups. Forty-four quantitative features estimated from a pooled dataset of 204 EEG recordings from 66 healthy adult volunteers who received either propofol, dexmedetomidine, or sevoflurane (all with and without remifentanil) were used in a machine learning based automated system to estimate the depth of sedation. Model training and evaluation were performed using leave-one-out cross validation methodology. We trained four machine learning models to predict sedation levels and evaluated the influence of remifentanil, age, and sex on the prediction performance. The area under the receiver-operator characteristic curve (AUC) was used to assess the performance of the prediction model. The ensemble tree with bagging outperformed other machine learning models and predicted sedation levels with an AUC = 0.88 (0.81-0.90). There were significant differences in the prediction probability of the automated systems when trained and tested across different age groups and sex. The performance of the EEG based sedation level prediction system is drug, sex, and age specific. Nonlinear machine-learning models using quantitative EEG features can accurately predict sedation levels. The results obtained in this study may provide a useful reference for developing next generation EEG based sedation level prediction systems using advanced machine learning algorithms. Clinical trial registration: NCT02043938 and NCT03143972.
Keywords: Anaesthesia; Consciousness Monitors; Electroencephalogram; Machine learning; Medical informatics.
Conflict of interest statement
M.M.R.F.S.: His research group/department received (over the last 3 years) research grants and consultancy fees from The Medicines Company (Parsippany, NJ, USA), Masimo (Irvine, CA, USA), Fresenius (Bad Homburg, Germany), Dräger (Lübeck, Germany), Paion (Aachen, Germany), and Medtronic (Dublin, Ireland). He receives royalties on intellectual property from Demed Medical (Temse, Belgium) and the Ghent University (Gent, Belgium). Other authors have no conflicts of interest to declare.
© 2020. The Author(s).
Figures
References
- Kang E, Jiang D, Ryu YK, Lim S, Kwak M, Gray CD, et al. Early postnatal exposure to isoflurane causes cognitive deficits and disrupts development of newborn hippocampal neurons via activation of the mTOR pathway. PLoS Biol. 2017;15:e2001246. doi: 10.1371/journal.pbio.2001246.
- Hays SR, Deshpande JK. Newly postulated neurodevelopmental risks of pediatric anesthesia: theories that could rock our world. J Urol. 2013;189:1222–1228. doi: 10.1016/j.juro.2012.11.090.
- Zurek AA, Yu J, Wang D-S, Haffey SC, Bridgwater EM, Penna A, et al. Sustained increase in α5GABAA receptor function impairs memory after anesthesia. J Clin Invest. 2014;124:5437. doi: 10.1172/JCI76669.
- Luk TT, Jia B, Pang EY, Lau VN, Lam CK, Chu MH, et al. Depth of anesthesia and postoperative delirium. Curr Anesthesiol Rep. 2015;5:1–9. doi: 10.1007/s40140-014-0088-z.
- Hajat Z, Ahmad N, Andrzejowski J. The role and limitations of EEG-based depth of anaesthesia monitoring in theatres and intensive care. Anaesthesia. 2017;72(Suppl 1):38–47. doi: 10.1111/anae.13739.
- Kreuzer M. EEG based monitoring of general anesthesia: taking the next steps. Front Comput Neurosci. 2017;11:56. doi: 10.3389/fncom.2017.00056.
- Li T-N, Li Y. Depth of anaesthesia monitors and the latest algorithms. Asian Pac J Trop Med. 2014;7:429–437. doi: 10.1016/S1995-7645(14)60070-5.
- Musialowicz T, Lahtinen P. Current status of EEG-based depth-of-consciousness monitoring during general anesthesia. Curr Anesthesiol Rep. 2014;4:251–260. doi: 10.1007/s40140-014-0061-x.
- Bibian S, Dumont GA, Zikov T. Dynamic behavior of BIS, M-entropy and neuroSENSE brain function monitors. J Clin Monit Comput. 2011;25:81–87. doi: 10.1007/s10877-010-9266-9.
- Bresson J, Gayat E, Agrawal G, Chazot T, Liu N, Hausser-Haw C, et al. A randomized controlled trial comparison of NeuroSENSE and Bispectral brain monitors during Propofol-based versus sevoflurane-based general anesthesia. Anesth Analg. 2015;121:1194–1201. doi: 10.1213/ANE.0000000000000922.
- Purdon PL, Sampson A, Pavone KJ, Brown EN. Clinical electroencephalography for Anesthesiologists Part I: background and basic signatures. J Am Soc Anesthesiol. 2015;123:937–960. doi: 10.1097/ALN.0000000000000841.
- Purdon, Pavone KJ, Akeju O, Smith AC, Sampson AL, Lee J, et al. The Ageing Brain: Age-dependent changes in the electroencephalogram during propofol and sevoflurane general anaesthesia. Br J Anaesth. 2015;115:i46–i57. doi: 10.1093/bja/aev213.
- Riphaus A, Slottje M, Bulla J, Keil C, Mentzel C, Limbach V, et al. Women awaken faster than men after electroencephalogram-monitored propofol sedation for colonoscopy: a prospective observational study. Eur J Anaesthesiol. 2017;34:681–687. doi: 10.1097/EJA.0000000000000665.
- Ramaswamy SM, Kuizenga MH, Weerink MA, Vereecke HE, Struys MM, Nagaraj SB. Novel drug-independent sedation level estimation based on machine learning of quantitative frontal electroencephalogram features in healthy volunteers. Br J Anaesth. 2019;123:479–487. doi: 10.1016/j.bja.2019.06.004.
- Kuizenga MH, Colin PJ, Reyntjens KMEM, Touw DJ, Nalbat H, Knotnerus FH, et al. Test of neural inertia in humans during general anaesthesia. Br J Anaesth. 2018;120:525–536. doi: 10.1016/j.bja.2017.11.072.
- Weerink MAS, Barends CRM, Muskiet ERR, Reyntjens KMEM, Knotnerus FH, Oostra M, et al. Pharmacodynamic interaction of remifentanil and dexmedetomidine on depth of sedation and tolerance of laryngoscopy. Anesthesiology. 2019;
- Schnider TW, Minto CF, Gambus PL, Andresen C, Goodale DB, Shafer SL, et al. The influence of method of administration and covariates on the pharmacokinetics of propofol in adult volunteers. Anesthesiology. 1998;88:1170–1182. doi: 10.1097/00000542-199805000-00006.
- Minto CF, Schnider TW, Short TG, Gregg KM, Gentilini A, Shafer SL. Response surface model for anesthetic drug interactions. Anesthesiology. 2000;92:1603–1616. doi: 10.1097/00000542-200006000-00017.
- Chernik DA, Gillings D, Laine H, Hendler J, Silver JM, Davidson AB, et al. Validity and reliability of the Observer’s: assessment of alertness/sedation scale: study with: intravenous midazolam. J Clin Psychopharmacol. 1990;10:244–251. doi: 10.1097/00004714-199008000-00003.
- Colin PJ, Hannivoort LN, Eleveld DJ, Reyntjens KMEM, Absalom AR, Vereecke HEM, et al. Dexmedetomidine pharmacokinetic-pharmacodynamic modelling in healthy volunteers: 1. Influence of arousal on bispectral index and sedation. Br J Anaesth. 2017;119:200–210. doi: 10.1093/bja/aex085.
- Eleveld DJ, Proost JH, Vereecke H, Absalom AR, Olofsen E, Vuyk J, et al. An allometric model of remifentanil pharmacokinetics and pharmacodynamics. Anesthesiol J Am Soc Anesthesiol. 2017;126:1005–1018.
- Hjorth B. EEG analysis based on time domain properties. Electroencephalogr Clin Neurophysiol. 1970;29:306–310. doi: 10.1016/0013-4694(70)90143-4.
- Stevenson N, Korotchikova I, Temko A, Lightbody G, Marnane W, Boylan G. An automated system for grading EEG abnormality in term neonates with hypoxic-ischaemic encephalopathy. Ann Biomed Eng. 2013;41:775–785. doi: 10.1007/s10439-012-0710-5.
- Brandon Westover M, Shafi MM, Ching S, Chemali JJ, Purdon PL, Cash SS, et al. Real-time segmentation of burst suppression patterns in critical care EEG monitoring. J Neurosci Methods. 2013;219:131–141. doi: 10.1016/j.jneumeth.2013.07.003.
- Sabatini AM. Analysis of postural sway using entropy measures of signal complexity. Med Biol Eng Comput. 2000;38:617–624. doi: 10.1007/BF02344866.
- Shannon CE. A mathematical theory of communication. ACM SIGMOBILE Mob Comput Commun Rev. 2001;5:3–55. doi: 10.1145/584091.584093.
- Liang Z, Wang Y, Sun X, Li D, Voss LJ, Sleigh JW, et al. EEG entropy measures in anesthesia. Front Comput Neurosci. 2015;9
- Grassberger P, Schreiber T, Schaffrath C. Nonlinear time sequence analysis. Int J Bifurc Chaos. 1991;01:521–547. doi: 10.1142/S0218127491000403.
- Kannathal N, Choo ML, Acharya UR, Sadasivan PK. Entropies for detection of epilepsy in EEG. Comput Methods Prog Biomed. 2005;80:187–194. doi: 10.1016/j.cmpb.2005.06.012.
- Bandt C, Pompe B. Permutation entropy: a natural complexity measure for time series. Phys Rev Lett. 2002;88:174102. doi: 10.1103/PhysRevLett.88.174102.
- Nan X, Jinghua X. The fractal dimension of EEG as a physical measure of conscious human brain activities. Bull Math Biol. 1988;50:559–565. doi: 10.1016/S0092-8240(88)80009-0.
- Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc Ser B Stat Methodol. 2005;67:301–320. doi: 10.1111/j.1467-9868.2005.00503.x.
- Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20:273–297.
- Breiman L. Random forests. Mach Learn. 2001;45:5–32. doi: 10.1023/A:1010933404324.
- Dietterich TG. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn. 2000;40:139–157. doi: 10.1023/A:1007607513941.
Source: PubMed