Automatic anesthesia depth staging using entropy measures and relative power of electroencephalogram frequency bands

  • Mercedeh Jahanseir
  • Seyed Kamaledin Setarehdan
  • Sirous Momenzadeh
Scientific Paper


Many of the surgeries performed under general anesthesia are aided by electroencephalogram (EEG) monitoring. With increased focus on detecting the anesthesia states of patients in the course of surgery, more attention has been paid to analyzing the power spectra and entropy measures of EEG signal during anesthesia. In this paper, by using the relative power of EEG frequency bands and the EEG entropy measures, a new method for detecting the depth of anesthesia states has been presented based on the least squares support vector machine (LS-SVM) classifiers. EEG signals were recorded from 20 patients before, during and after general anesthesia in the operating room at a sampling rate of 200 Hz. Then, 12 features were extracted from each EEG segment, 10 s in length, which are used for anesthesia state monitoring. No significant difference was observed (p > 0.05) between these features and the bispectral index (BIS), which is the commonly used measure of anesthetic effect. The used LS-SVM classifier based method is able to identify the anesthesia states with an accuracy of 80% with reference to the BIS index. Since the underlying equation of the utilized LS-SVM is linear, the computational time of the algorithm is not significant and therefore it can be used for online application in operation rooms.


Electroencephalogram Anesthesia Entropy Power spectra LS-SVM 


Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. 1.
    Miller RD, Pardo M (2011) Basics of anesthesia e-book. Elsevier Health Sciences, New YorkGoogle Scholar
  2. 2.
    Mędrzycka-Dąbrowska W, Dąbrowski S, Gutysz-Wojnicka A et al (2017) Unintended return of consciousness in a patient during surgery and general anesthesia. Eur Neurol 77:262–266CrossRefGoogle Scholar
  3. 3.
    Sebel PS, Bowdle TA, Ghoneim MM et al (2004) The incidence of awareness during anesthesia: a multicenter United States study. Anesth Analg 99:833–839CrossRefGoogle Scholar
  4. 4.
    Wei Q, Liu Q, Fan S-Z et al (2013) Analysis of EEG via multivariate empirical mode decomposition for depth of anesthesia based on sample entropy. Entropy 15:3458–3470CrossRefGoogle Scholar
  5. 5.
    Barash P, Cullen BF, Stoelting RK et al (2013) Handbook of clinical anesthesia. Lippincott Williams & Wilkins, PhiladelphiaGoogle Scholar
  6. 6.
    Koch S, Stegherr A, Mörgeli R et al (2017) Electroencephalogram dynamics in children during different levels of anaesthetic depth. Clin Neurophysiol 128:2014–2021CrossRefGoogle Scholar
  7. 7.
    Wang J, Zhang L, Huang Q et al (2017) Monitoring the end-tidal concentration of sevoflurane for preventing awareness during anesthesia (MEETS-PANDA): a prospective clinical trial. Int J Surg 41:44–49CrossRefGoogle Scholar
  8. 8.
    Li D, Hambrecht-Wiedbusch VS, Mashour GA (2017) Accelerated recovery of consciousness after general anesthesia is associated with increased functional brain connectivity in the high-gamma bandwidth. Front Syst Neurosci 11:16PubMedPubMedCentralGoogle Scholar
  9. 9.
    Gaskell A, Hight D, Winders J et al (2017) Frontal alpha-delta EEG does not preclude volitional response during anaesthesia: prospective cohort study of the isolated forearm technique. BJA Br J Anaesth 119:664–673CrossRefGoogle Scholar
  10. 10.
    Vasella FC, Frascarolo P, Spahn D, Magnusson L (2005) Antagonism of neuromuscular blockade but not muscle relaxation affects depth of anaesthesia. Br J Anaesth 94:742–747CrossRefGoogle Scholar
  11. 11.
    Guignard B (2006) Monitoring analgesia. Best Pract Res Clin Anaesth 20:161–180CrossRefGoogle Scholar
  12. 12.
    Chernik DA, Gillings D, Laine H et al (1990) Validity and reliability of the observer’s: assessment of alertness/sedation scale: study with: intravenous midazolam. J Clin Psychopharmacol 10:244–251CrossRefGoogle Scholar
  13. 13.
    Lan J-Y, Abbod MF, Yeh R-G et al (2012) Intelligent modeling and control in anesthesia. J Med Biol Eng 32:293–308CrossRefGoogle Scholar
  14. 14.
    Nunes RR, Chaves IMM, de Alencar JCG et al (2012) Bispectral index and other processed parameters of electroencephalogram: an update. Braz J Anesth 62:105–117Google Scholar
  15. 15.
    Liu Q, Wei Q, Fan S-Z et al (2012) Adaptive computation of multiscale entropy and its application in EEG signals for monitoring depth of anesthesia during surgery. Entropy 14:978–992CrossRefGoogle Scholar
  16. 16.
    Mueller JN, Kreuzer M, Garcia PS et al (2017) Monitoring depth of sedation: evaluating the agreement between the bispectral index, qCON and the entropy module’s state entropy during flexible bronchoscopy. Minerva Anestesiol 83:563–573Google Scholar
  17. 17.
    Sciusco A, Standing JF, Sheng Y et al (2017) Effect of age on the performance of bispectral and entropy indices during sevoflurane pediatric anesthesia: a pharmacometric study. Pediatr Anesth 27:399–408CrossRefGoogle Scholar
  18. 18.
    Liang Z, Wang Y, Sun X et al (2015) EEG entropy measures in anesthesia. Front Comput Neurosci 9:16CrossRefGoogle Scholar
  19. 19.
    Chao A, Jost L, Hsieh T et al (2015) Expected Shannon entropy and Shannon differentiation between subpopulations for neutral genes under the finite island model. PloS ONE 10:e0125471CrossRefGoogle Scholar
  20. 20.
    Gifani P, Rabiee H, Hashemi M et al (2007) Optimal fractal-scaling analysis of human EEG dynamic for depth of anesthesia quantification. J Frankl Inst 344:212–229CrossRefGoogle Scholar
  21. 21.
    Kumar L, Sripada SK, Sureka A, Rath SK (2017) Effective fault prediction model developed using least square support vector machine (LSSVM). J Syst Softw 137:686–712CrossRefGoogle Scholar
  22. 22.
    Kumar D, Tripathy RK, Acharya A (2014) Least square support vector machine based multiclass classification of EEG signals. WSEAS Trans Signal Process 10:86–94Google Scholar
  23. 23.
    Al-Qammaz AYA, Ahmad FK, Yusof Y (2016) Optimization of least squares support vector machine technique using genetic algorithm for electroencephalogram multi-dimensional signals. J Teknol 78:107–115Google Scholar
  24. 24.
    Shalbaf R, Behnam H, Moghadam HJ et al (2013) The brain function index as a depth of anesthesia indicator using complexity measures. In: Systems, Process & Control (ICSPC), 2013 IEEE conference, pp 68–72Google Scholar
  25. 25.
    Hagihira S (2017) Brain mechanisms during course of anesthesia: what we know from EEG changes during induction and recovery. Front Syst Neurosci 11:39CrossRefGoogle Scholar
  26. 26.
    Carbone P, Petri D, Barbé K (2017) Nonparametric probability density estimation via interpolation filtering. IEEE Trans Instrum Meas 66:681–690CrossRefGoogle Scholar
  27. 27.
    Stoica P, Moses RL (2005) Spectral analysis of signals. Pearson Prentice Hall, Upper Saddle RiverGoogle Scholar
  28. 28.
    Bayat M, Abdollahi HV (2016) Various types of parametric methods of power spectral density estimation 6(19):2719–2735Google Scholar
  29. 29.
    Mulye A (2016) Power spectrum density estimation methods for michelson interferometer wavemeters. Doctoral dissertation, University of OttawaGoogle Scholar
  30. 30.
    Schuster A (1906) The periodogram and its optical analogy. Proc R Soc Lond A 77:136–140CrossRefGoogle Scholar
  31. 31.
    Schuster S, Scheiblhofer S, Stelzer A (2009) The influence of windowing on bias and variance of DFT-based frequency and phase estimation. IEEE Trans Instrum Meas 58:1975–1990CrossRefGoogle Scholar
  32. 32.
    Rahi PK, Mehra R (2014) Analysis of power spectrum estimation using welch method for various window techniques. Int J Emerg Technol Eng 2:106–109Google Scholar
  33. 33.
    Gupta HR, Mehra R (2013) Power spectrum estimation using Welch method for various window techniques. Int J Sci Res Eng Technol (IJSRET) 2:389–392Google Scholar
  34. 34.
    Barbe K, Pintelon R, Schoukens J (2010) Welch method revisited: nonparametric power spectrum estimation via circular overlap. IEEE Trans Signal Process 58:553–565CrossRefGoogle Scholar
  35. 35.
    Rodríguez-Sotelo LJ, Osorio-Forero A, Jiménez-Rodríguez A et al (2014) Automatic sleep stages classification using EEG entropy features and unsupervised pattern analysis techniques. Entropy. CrossRefGoogle Scholar
  36. 36.
    Azemin MZC, Ab Hamid F, Wang JJ et al (2016) Box-counting fractal dimension algorithm variations on retina images. In: Rosso OA (ed) Advanced computer and communication engineering technology. Springer, New York, pp 337–343CrossRefGoogle Scholar
  37. 37.
    Ai T, Zhang R, Zhou H, Pei J (2014) Box-counting methods to directly estimate the fractal dimension of a rock surface. Appl Surf Sci 314:610–621CrossRefGoogle Scholar
  38. 38.
    Xu L, Ivanov PC, Hu K et al (2005) Quantifying signals with power-law correlations: a comparative study of detrended fluctuation analysis and detrended moving average techniques. Phys Rev E 71:051101CrossRefGoogle Scholar
  39. 39.
    Hu K, Ivanov PC, Chen Z et al (2001) Effect of trends on detrended fluctuation analysis. Phys Rev E 64:011114CrossRefGoogle Scholar
  40. 40.
    Li X, Jiang Y, Hong J et al (2016) Estimation of cognitive workload by approximate entropy of EEG. J Mech Med Biol 16:1650077CrossRefGoogle Scholar
  41. 41.
    Sun R, Wong W, Wang J, Tong RK (2017) Changes in electroencephalography complexity using a brain computer interface-motor observation training in chronic stroke patients: a fuzzy approximate entropy analysis. Front Human Neurosci 11:444CrossRefGoogle Scholar
  42. 42.
    Zanin M, Zunino L, Rosso OA, Papo D (2012) Permutation entropy and its main biomedical and econophysics applications: a review. Entropy 14:1553–1577CrossRefGoogle Scholar
  43. 43.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  44. 44.
    Suykens JA, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9:293–300CrossRefGoogle Scholar
  45. 45.
    Suykens JA, Van Gestel T, De Brabanter J et al (2002) Least squares support vector machines. World Scientific, SingaporeCrossRefGoogle Scholar
  46. 46.
    Caviness JN, Lue L, Hentz JG et al (2016) Cortical phosphorylated α-synuclein levels correlate with brain wave spectra in Parkinson’s disease. Mov Disord 31:1012–1019CrossRefGoogle Scholar
  47. 47.
    Grønli J, Rempe MJ, Clegern WC et al (2016) Beta EEG reflects sensory processing in active wakefulness and homeostatic sleep drive in quiet wakefulness. J Sleep Res 25:257–268CrossRefGoogle Scholar
  48. 48.
    Reed S (2012) Differential effects of propofol on gamma-band activity across cortical and thalamic sites in the rat, in vivo. Doctoral dissertation, McGill University LibrariesGoogle Scholar
  49. 49.
    Breshears JD, Roland JL, Sharma M et al (2010) Stable and dynamic cortical electrophysiology of induction and emergence with propofol anesthesia. Proc Natl Acad Sci 107:21170–21175CrossRefGoogle Scholar
  50. 50.
    Purdon PL, Pierce ET, Mukamel EA et al (2013) Electroencephalogram signatures of loss and recovery of consciousness from propofol. Proc Natl Acad Sci 110:E1142–E1151CrossRefGoogle Scholar
  51. 51.
    Kreuzer M (2017) EEG based monitoring of general anesthesia: taking the next steps. Front Comput Neurosci 11:56CrossRefGoogle Scholar
  52. 52.
    Dumont GA (2014) Monitoring the EEG for assessing depth of anesthesia. In: Ehrenfeld JM, Cannesson M (eds) Monitoring technologies in acute care environments. Springer, New York, pp 255–260CrossRefGoogle Scholar
  53. 53.
    Hashemi M, Hutt A, Hight D, Sleigh J (2017) Anesthetic action on the transmission delay between cortex and thalamus explains the beta-buzz observed under propofol anesthesia. PloS ONE 12:e0179286CrossRefGoogle Scholar
  54. 54.
    Ching S, Brown EN (2014) Modeling the dynamical effects of anesthesia on brain circuits. Curr Opin Neurobiol 25:116–122CrossRefGoogle Scholar
  55. 55.
    Hindriks R, van Putten MJ (2012) Meanfield modeling of propofol-induced changes in spontaneous EEG rhythms. Neuroimage 60:2323–2334CrossRefGoogle Scholar
  56. 56.
    Ma Y, Shi W, Peng C-K, Yang AC (2017) Nonlinear dynamical analysis of sleep electroencephalography using fractal and entropy approaches. Sleep Med Rev. CrossRefPubMedGoogle Scholar
  57. 57.
    Zeng K, Ouyang G, Chen H et al (2018) Characterizing dynamics of absence seizure EEG with spatial-temporal permutation entropy. Neurocomput 275:577–585CrossRefGoogle Scholar
  58. 58.
    Zunino L, Olivares F, Scholkmann F, Rosso OA (2017) Permutation entropy based time series analysis: equalities in the input signal can lead to false conclusions. Phys Lett A 381:1883–1892CrossRefGoogle Scholar
  59. 59.
    Su C, Liang Z, Li X et al (2016) A comparison of multiscale permutation entropy measures in on-line depth of anesthesia monitoring. PloS ONE 11:e0164104CrossRefGoogle Scholar
  60. 60.
    Kuhlmann L, Manton JH, Heyse B et al (2017) Tracking electroencephalographic changes using distributions of linear models: application to propofol-based depth of anesthesia monitoring. IEEE Trans Biomed Eng 64:870–881CrossRefGoogle Scholar

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2018

Authors and Affiliations

  • Mercedeh Jahanseir
    • 1
  • Seyed Kamaledin Setarehdan
    • 2
  • Sirous Momenzadeh
    • 3
  1. 1.Department of Biomedical Engineering, Science and Research BranchIslamic Azad UniversityTehranIran
  2. 2.Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, College of EngineeringUniversity of TehranTehranIran
  3. 3.Functional Neurosurgery Research CenterShahid Beheshti University of Medical SciencesTehranIran

Personalised recommendations