Robust approach to depth of anaesthesia assessment based on hybrid transform and statistical features
- Author(s): Mohammed Diykh 1, 2 ; Firas Sabar Miften 2 ; Shahab Abdulla 3 ; Khalid Saleh 4 ; Jonathan H. Green 3, 5
-
-
View affiliations
-
Affiliations:
1:
School of Agricultural, Computational and Environmental Sciences , University of Southern Queensland , Australia ;
2: University of Thi-Qar , College of Education for Pure Science , Iraq ;
3: Open Access College , University of Southern Queensland , Australia ;
4: School of Mechanical and Electrical Engineering , University of Southern Queensland , Australia ;
5: Faculty of the Humanities , University of the Free State , South Africa
-
Affiliations:
1:
School of Agricultural, Computational and Environmental Sciences , University of Southern Queensland , Australia ;
- Source:
Volume 14, Issue 1,
January
2020,
p.
128 – 136
DOI: 10.1049/iet-smt.2018.5393 , Print ISSN 1751-8822, Online ISSN 1751-8830
- « Previous Article
- Table of contents
- Next Article »
To develop an accurate and efficient depth of anaesthesia (DoA) assessment technique that could help anaesthesiologists to trace the patient's anaesthetic state during surgery, a new automated DoA approach was proposed. It applied wavelet-Fourier analysis (WFA) to extract the statistical characteristics from an anaesthetic electroencephalogram (EEG) signal and to design a new DoA index. In this proposed method, firstly, the wavelet transform was applied to a denoised EEG signal, and a fast Fourier transform was then applied to the wavelet detail coefficient D3. Ten statistical features were extracted and analysed, and from these, five features were selected for designing a new index for the DoA assessment. Finally, a new DoA () was developed and compared with the most popular bispectral index (BIS) monitor. The results from the testing set showed that there were very high correlations between the and the BIS index during the awake, light and deep anaesthetic stages. In the case of poor signal quality, the BIS index and the were also tested, and the obtained results demonstrated that the could indicate the DoA values, while the BIS failed to show valid outputs for those situations.
Inspec keywords: electroencephalography; surgery; medical signal processing; statistical analysis; feature extraction; feature selection; wavelet transforms; neurophysiology; signal denoising; direction-of-arrival estimation; fast Fourier transforms; patient monitoring
Other keywords: efficient depth; DoA values; hybrid transform; wavelet transform; statistical feature extraction; BIS index; DoA index; surgery; DoA assessment; wavelet-Fourier analysis; denoised EEG signal; anaesthetic electroencephalogram signal; feature selection; patient anaesthetic state; automated DoA approach; robust approach; bispectral index monitor; EEG; anaesthesia assessment technique; fast Fourier transform
Subjects: Function theory, analysis; Biology and medical computing; Electrodiagnostics and other electrical measurement techniques; Patient care and treatment; Other topics in statistics; Digital signal processing; Integral transforms; Signal processing and detection; Integral transforms; Bioelectric signals; Electrical activity in neurophysiological processes; Probability theory, stochastic processes, and statistics; Patient care and treatment; Other topics in statistics
References
-
-
1)
-
35. Petsiti, A., Tassoudis, V., Vretzakis, G., et al: ‘Depth of anesthesia as a risk factor for perioperative morbidity’, Anesthesiol. Res. Pract., 2015, 2015, p. 301291.
-
-
2)
-
26. Nguyen-Ky, T., Wen, P., Li, Y., et al: ‘Measuring and reflecting depth of anesthesia using wavelet and power spectral density’, IEEE Trans. Inf. Technol. Biomed., 2011, 15, (4), pp. 630–639.
-
-
3)
-
9. Esmaeili, V., Assareh, A., Shamsollahi, M., et al: ‘Estimating the depth of anesthesia using fuzzy soft computation applied to Eeg’, Intell. Data Anal., 2008, 12, pp. 393–407.
-
-
4)
-
7. Constant, I., Sabourdin, N.: ‘Monitoring depth of anesthesia: from consciousness to nociception. A window on subcortical brain activity’, Pediatric Anesthesia, 2015, 25, (1), pp. 73–82.
-
-
5)
-
28. Staikou, C., Paraskeva, A., Karmaniolou, I., et al: ‘Intravenous lidocaine does not affect the anesthetic depth during rapid sequence induction and intubation as assessed by bispectral index monitoring: a randomized double blind study’, Arch. Med. Sci., 2013, 9, (4), p. 713.
-
-
6)
-
6. Çalişkan, A., Çevik, U.: ‘An efficient noisy pixels detection model for Ct images using extreme learning machines’, Tehnički Vjesnik, 2018, 25, (3), pp. 679–686.
-
-
7)
-
8. Dusan, O.L.M., Rosas, D.A.B., Cagy, M., et al: ‘Nonlinear analysis of the electroencephalogram in depth of anesthesia’, Revista Facultad de Ingeniería, 2015, 8, (75), pp. 45–56.
-
-
8)
-
19. Li, T., Peng, W.: ‘Depth of anaesthesia assessment using interval second-order difference plot and permutation entropy techniques’, IET Signal Process., 2016, 11, (2), pp. 221–227.
-
-
9)
-
34. Palendeng, M.E., Wen, P., Li, Y.: ‘Real-time depth of anaesthesia assessment using strong analytical signal transform technique’, Australas. Phys. Eng. Sci. Med., 2014, 37, (4), pp. 723–730.
-
-
10)
-
32. Shalbaf, R., Behnam, H., Sleigh, J.W., et al: ‘Monitoring the depth of anesthesia using entropy features and an artificial neural network’, J. Neurosci. Methods, 2013, 218, (1), pp. 17–24.
-
-
11)
-
2. Ball, C., Westhorpe, R.: ‘The history of depth of anaesthesia monitoring’, Anaesth. Intensive Care, 2010, 38, (5), pp. 797–798.
-
-
12)
-
25. Nguyen-Ky, T., Wen, P., Li, Y.: ‘Consciousness and depth of anesthesia assessment based on Bayesian analysis of Eeg signals’, IEEE Trans. Biomed. Eng., 2013, 60, (6), pp. 1488–1498.
-
-
13)
-
20. Liu, Q., Chen, Y.-F., Fan, S.-Z., et al: ‘Eeg signals analysis using multiscale entropy for depth of anesthesia monitoring during surgery through artificial neural networks’, Comput. Math. Methods Med., 2015, 2015, p. 232381.
-
-
14)
-
33. Shi, L., Li, X., Wan, H.: ‘A predictive model of anesthesia depth based on Svm in the primary visual cortex’, Open. Biomed. Eng. J., 2013, 7, p. 71.
-
-
15)
-
41. Ziółko, B., Kozłowski, W., Ziółko, M., et al: ‘Hybrid wavelet-Fourier-hmm speaker recognition’, Int. J. Hybrid Inf. Technol., 2011, 4, (4), pp. 21–25.
-
-
16)
-
21. Moca, V.V., Scheller, B., Mureşan, R.C., et al: ‘Eeg under anesthesia – feature extraction with Tespar’, Comput. Methods Programs Biomed., 2009, 95, (3), pp. 191–202.
-
-
17)
-
5. Bibian, S., Zikov, T., Dumont, G.A., et al: ‘Estimation of the anesthetic depth using wavelet analysis of electroencephalogram’, DTIC Document, 2001.
-
-
18)
-
14. Jameson, L.C., Sloan, T.B.: ‘Using Eeg to monitor anesthesia drug effects during surgery’, J. Clin. Monit. Comput., 2006, 20, (6), pp. 445–472.
-
-
19)
-
42. Spitellie, P.H., Holmes, M.A., Domino, K.B.: ‘Awareness during anesthesia’, Anesthesiol. Clin. North. America., 2002, 20, (3), pp. 555–570.
-
-
20)
-
38. Zheng, Y., Essock, E.A.: ‘Novel feature extraction method-wavelet-Fourier analysis and its application to glaucoma classification’. Proc. of 7th Joint Conf. on Information Sciences, North Carolina, USA, 2003.
-
-
21)
-
40. Tünsmeyer, J., Hopster, K., Kästner, S.B.: ‘Clinical use of a multivariate electroencephalogram (Narcotrend) for assessment of anesthetic depth in horses during isoflurane–xylazine anesthesia’, Front. Vet. Sci., 2016, 3.
-
-
22)
-
12. Hardman, J.G., Aitkenhead, A.R.: ‘Awareness during anaesthesia’, Continuing Educ. Anaesthesia Critical Care Pain, 2005, 5, (6), pp. 183–186.
-
-
23)
-
24. Nguyen-Ky, T., Wen, P., Li, Y.: ‘Theoretical basis for identification of different anesthetic states based on routinely recorded Eeg during operation’, Comput. Biol. Med., 2009, 39, (1), pp. 40–45.
-
-
24)
-
22. Mousavi, S.M., Adamoğlu, A., Demiralp, T., et al: ‘A wavelet transform based method to determine depth of anesthesia to prevent awareness during general anesthesia’, Comput. Math. Methods Med., 2014, 2014, p. 354739.
-
-
25)
-
15. Jospin, M., Caminal, P., Jensen, E.W., et al: ‘Detrended fluctuation analysis of Eeg as a measure of depth of anesthesia’, IEEE Trans. Biomed. Eng., 2007, 54, (5), pp. 840–846.
-
-
26)
-
23. Nguyen-Ky, T., Wen, P., Li, Y.: ‘Modified detrended fluctuation analysis method in depth of anesthesia assessment application’. Proc. of the Int. Conf. on Bioinformatics and Computational Biology (BIOCOMP 2008), Las Vegas, USA, 2008.
-
-
27)
-
4. Bard, J.W.: ‘The Bis monitor: a review and technology assessment’, AANA J., 2001, 69, (6), pp. 477–484.
-
-
28)
-
36. Tarasiuk, T.: ‘Hybrid wavelet-Fourier spectrum analysis’, IEEE Trans. Power Deliv., 2004, 19, (3), pp. 957–964.
-
-
29)
-
10. Fu, K., Qu, J., Chai, Y., et al: ‘Classification of seizure based on the time–frequency image of Eeg signals using Hht and Svm’, Biomed. Signal Proc. Control, 2014, 13, pp. 15–22.
-
-
30)
-
11. Giavarina, D.: ‘Understanding bland altman analysis’, Biochem. Med. (Zagreb), 2015, 25, (2), pp. 141–151.
-
-
31)
-
16. Lalitha, V., Eswaran, C.: ‘Automated detection of anesthetic depth levels using chaotic features with artificial neural networks’, J. Med. Syst., 2007, 31, (6), pp. 445–452.
-
-
32)
-
31. Shalbaf, R., Behnam, H., Moghadam, H.J.: ‘Monitoring depth of anesthesia using combination of Eeg measure and hemodynamic variables’, Cogn. Neurodyn., 2014, 9, (1), pp. 41–51.
-
-
33)
-
3. Bankman, I., Gath, I.: ‘Feature extraction and clustering of Eeg during anesthesia’, Med. Biol. Comput., 1987, 25, (4), pp. 474–477.
-
-
34)
-
39. Shaker, M.M.: ‘Eeg waves classifier using wavelet transform and Fourier transform’, Int. Journal of Biological and Life Sciences, 2005, 1, pp. 85–90.
-
-
35)
-
17. Li, T., Wen, P., Jayamaha, S.: ‘Anaesthetic Eeg signal denoise using improved nonlocal mean methods’, Australas. Phys. Eng. Sci. Med., 2014, 37, (2), pp. 431–437.
-
-
36)
-
37. Tupaika, N., Vallverdu, M., Jospin, M., et al: ‘Assessment of the depth of anesthesia based on symbolic dynamics of the Eeg’. 2010 Annual Int. Conf. of the IEEE Engineering in Medicine and Biology Society (EMBC), Buenos Aires, Argentina, 2010.
-
-
37)
-
27. Nicolaou, N., Hourris, S., Alexandrou, P., et al: ‘Eeg-based automatic classification of ‘awake'versus ‘anesthetized'state in general anesthesia using granger causality’, PLOS One, 2012, 7, (3), p. e33869.
-
-
38)
-
13. Hasak, L., Wujtewicz, M., Owczuk, R.: ‘Assessment of the depth of anaesthesia during inhalational and intravenous induction of general anaesthesia’, Anaesthesiol. Intensive. Ther., 2014, 46, (4), pp. 274–279.
-
-
39)
-
1. Arslan, A., Sen, B., Çelebi, F.V., et al: ‘A comparison of different classification algorithms for determining the depth of anesthesia level on a new set of attributes’. 2015 Int. Symp. on Innovations in Intelligent SysTems and Applications (INISTA), Madrid, Spain, 2015.
-
-
40)
-
18. Li, T.-N., Li, Y.: ‘Depth of anaesthesia monitors and the latest algorithms’, Asian Pac. J. Trop. Med., 2014, 7, (6), pp. 429–437.
-
-
41)
-
29. Shepherd, J., Jones, J., Frampton, G., et al: ‘Clinical effectiveness and cost-effectiveness of depth of anaesthesia monitoring (e-entropy, bispectral index and narcotrend): a systematic review and economic evaluation’, Health Technol. Assess., 2013, 17, (34), pp. 1–264.
-
-
42)
-
30. Tiren, C., Barr, G., Anderson, R., et al: ‘Depth of anaesthesia monitoring: a clinical study comparing Bis and Aai during heart surgery: A-149’, Eur. J. Anaesthesiol., 2004, 21, pp. 37–38.
-
-
1)