Characterization of Daytime Sleepiness by Time–Frequency Measures of EEG Signals

  • Umberto Melia
  • Marc Guaita
  • Montserrat Vallverdú
  • Francesc Clariá
  • Josep M. Montserrat
  • Isabel Vilaseca
  • Manel Salamero
  • Carles Gaig
  • Pere Caminal
  • Joan Santamaria
Original Article

Abstract

Excessive daytime sleepiness (EDS) is one of the main symptoms of several sleep-related disorders with a great impact on patient lives. While many studies have been carried out in order to assess daytime sleepiness, automatic EDS detection still remains an open problem. In this work, a detection approach based on the time–frequency analysis of electroencephalography (EEG) signals is proposed. Multichannel EEG signals were recorded during five maintenance of wakefulness (MWT) and multiple sleep latency tests alternated throughout the day from patients suffering from sleep-disordered breathing. A group of 20 patients with EDS was compared with a group of 20 patients without daytime sleepiness (WDS) by analyzing 60-s EEG windows in the waking state. Measures obtained from the Choi–Williams distribution (CWD) and the cross-CWD were calculated in the EEG frequency bands δ (0.1–4 Hz), θ (4–8 Hz), α (8–12 Hz), β (12–30 Hz), and total band (TB, 0.1–45 Hz). Statistical differences between EDS and WDS groups were found in the δ and θ bands during MWT events (p < 0.0001). The results show that the EDS group presented more power in the θ band, while the WDS group presented higher spectral and cross-spectral entropy in the frontal zone in the δ band. In general, CWD and cross-CWD measures yielded sensitivities and specificities of above 80 %. The area under the receiver operating characteristic curve was above 0.85 for classifying EDS and WDS patients.

Keywords

Biomedical signal processing Time–frequency representation Electroencephalography Excessive daytime sleepiness 

Abbreviations

EEG

Scalp-recorded electroencephalogram

MWT

Maintenance of wakefulness test

MSLT

Multiple sleep latency test

CWD

Choi–Williams distribution

EDS

Excessive daytime sleepiness

WDS

Without daytime sleepiness

AUC

Area under receiver operating characteristic curve

PSD

Power spectral density

TFR

Time–frequency representation

IP

Instantaneous power

IF

Instantaneous frequency

ISE

Instantaneous spectral entropy

Shan

Shannon entropy

Re

Rényi entropy

M

Mean

med

Median

max

Maximum

min

Minimum

std

Standard deviation

Pδ

Spectral power in δ band

Pθ

Spectral power in θ band

Pα

Spectral power in α band

Pβ

Spectral power in β band

TB

Total frequency band

mF

Mean frequency

SEF

Spectral edge frequency

Cf

Coherence function

Sen

Sensitivity

Spe

Specificity

References

  1. 1.
    Arand, D., Bonnet, M., Hurwitz, T., Mitler, M., Rosa, R., & Sangal, R. B. (2005). The clinical use of the MSLT and MWT. Sleep, 28, 123–144.Google Scholar
  2. 2.
    Lombardi, C., Parati, G., Cortelli, P., Provini, F., Vetrugno, R., Plazzi, G., & Vignatelli, L. (2008). Daytime sleepiness and neural cardiac modulation in sleeprelated breathing disorders. Journal of Sleep Research, 17, 263–270.CrossRefGoogle Scholar
  3. 3.
    Ohayon, M. M. (2008). From wakefulness to excessive sleepiness: what we know and still need to know. Sleep Medicine Reviews, 12, 129–141.CrossRefGoogle Scholar
  4. 4.
    Santamaria, J., & Chiappa, K. H. (1987). The EEG of drowsiness in normal adults. Journal of Clinical Neurophysiology, 4, 327–382.CrossRefGoogle Scholar
  5. 5.
    Jung, T. & Makeig, S. (1994). Estimating levels of alertness from EEG. In Proceedings on IEEE- EMBS Conference (pp. 1103–1104).Google Scholar
  6. 6.
    Makeig, S., & Inlow, M. (1993). Lapses in alertness: Coherence of fluctuations in performance and EEG spectrum. Electroencephalography and Clinical Neurophysiology, 86, 23–35.CrossRefGoogle Scholar
  7. 7.
    Gusnard, D. A., Akbudak, E., Shulman, G. L., & Raichle, M. E. (2001). Medial prefrontal cortex and self-referential mental activity: Relation to a default mode of brain function. Proceedings of the National Academy of Sciences of the United States of America, 98, 4259–4264.CrossRefGoogle Scholar
  8. 8.
    Vanhaudenhuyse, A., Demertzi, A., Schabus, M., Noirhomme, Q., Bredart, S., Boly, M., & Laureys, S. (2010). Two distinct neuronal networks mediate the awareness of environment and of self. Journal of Cognitive Neuroscience, 1, 1–9.CrossRefGoogle Scholar
  9. 9.
    Johnson, R. R., Popovic, P. D., Olmstead, R. E., Stikic, M., Levendowski, D. J., & Berka, C. (2011). Drowsiness/alertness algorithm development and validation using synchronized EEG and cognitive performance to individualize a generalized model. Biological Psychology, 87, 241–250.CrossRefGoogle Scholar
  10. 10.
    Swarnkar, V., Abeyratne, U., & Hukins, C. (2010). Objective measure of sleepiness and sleep latency via bispectrum analysis of EEG. Medical & Biological Engineering & Computing, 48, 1203–1213.CrossRefGoogle Scholar
  11. 11.
    Smith, M. E., McEvoy, L. K., & Gevins, A. (2002). The impact of moderate sleep loss on neurophysiologic signals during working-memory task performance. Sleep, 25, 784–794.Google Scholar
  12. 12.
    Chiou, J. C., Ko, L. W., Lin, C. T., Hong C. T., Jung T. P., Liang S. F., & Jeng, J. L. (2006). Using novel MEMS EEG sensors in detecting drowsiness application. In Proceedings. of biomedical circuits and systems conference London, (pp. 33–36).Google Scholar
  13. 13.
    Subasi, A., & Erçelebi, E. (2005). Classification of EEG signals using neural network and logistic regression. Computer Methods and Programs in Biomedicine, 78, 87–99.CrossRefGoogle Scholar
  14. 14.
    Fu, J., Li, M., & Lu, B. L. (2008). “Detecting drowsiness in driving simulation based on EEG”, Autonomous Systems–Self-Organization. Management, and Control, 1, 21–28.Google Scholar
  15. 15.
    Lin, C. T., Wu, R. C., Jung, T. P., Liang, S. F., & Huang, T. Y. (2005). Estimating driving performance based on EEG spectrum analysis. EURASIP Journal on Advances in Signal Processing, 19, 3165–3174.CrossRefGoogle Scholar
  16. 16.
    Wilson, B. J., & Bracewell, T. D. (2000). Alertness monitor using neural networks for EEG analysis. Proceedings on Neural Net Signal Process X (ISPS), 2, 814–820.Google Scholar
  17. 17.
    Vuckovic, V., Radivojevic, N., Chen, A. C., & Popovic, D. (2002). Automatic recognition of alertness and drowsiness from EEG by an artificial neural network. Medical Engineering & Physics, 24, 349–360.CrossRefGoogle Scholar
  18. 18.
    Yeo, M. V., Li, X., Shen, K., & Wilder-Smith, E. P. (2009). Can SVM be used for automatic EEG detection of drowsiness during car driving? Safety Science, 47, 115–124.CrossRefGoogle Scholar
  19. 19.
    Wacker, M., & Witte, H. (2013). Time–frequency techniques in biomedical signal analysis. A tutorial review of similarities and differences. Methods of Information in Medicine, 52, 279–296.CrossRefGoogle Scholar
  20. 20.
    Sitnikova, E., Hramov, A. E., Koronovsky, A. A., & van Luijtelaar, G. (2009). Sleep spindles and spike–wave discharges in EEG: Their generic features, similarities and distinctions disclosed with Fourier transform and continuous wavelet analysis. Journal of Neuroscience Methods, 180, 304–316.CrossRefGoogle Scholar
  21. 21.
    Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., & Liu, H. H. (1998). The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London A, 454, 903–995.MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Rehman, N., & Mandic, D. P. (2010). Multivariate empirical mode decomposition. Proceedings of the Royal Society of London A, 466, 1291–1302.MathSciNetCrossRefMATHGoogle Scholar
  23. 23.
    Li, X., Li, D., Liang, Z., Voss, L. J., & Sleigh, J. W. (2008). Analysis of depth of anesthesia with Hilbert-Huang spectral entropy. Clinical Neurophysiology, 119, 2465–2475.CrossRefGoogle Scholar
  24. 24.
    Zhang, A., Yang, B., & Huang, L. (2008). Feature extraction of EEG signals using power spectral entropy. International Conference on Biomedical Engineering Information, 2, 435–439.Google Scholar
  25. 25.
    Burioka, N., Miyata, M., Cornélissen, G., Halberg, F., Takeshima, T., Kaplan, D. T., & Shimizu, E. (2005). Approximate entropy in the electroencephalogram during wake and sleep. Clinical EEG Neuroscience, 36, 21–24.CrossRefGoogle Scholar
  26. 26.
    Chouvarda, I., Rosso, V., Mendez, M. O., Bianchi, A. M., Parrino, L., Grassi, A., et al. (2011). Assessment of the EEG complexity during activations from sleep. Computer Methods and Programs in Biomedicine, 104, e16–e28.CrossRefGoogle Scholar
  27. 27.
    Costa, M., Goldberger, A. L., & Peng, C. K. (2005). Multiscale entropy analysis of biological signals. Physical Review E, 71, 021906–021918.MathSciNetCrossRefGoogle Scholar
  28. 28.
    He, W. X., Yan, X. G., Chen, X. P., & Liu, H. (2005). Nonlinear feature extraction of sleeping EEG signals. In 27th annual international conference of the engineering in medicine and biology society, (pp. 4614–4617).Google Scholar
  29. 29.
    Carskadon, M. A., Dement, W. C., Mitler, M. M., Roth, T., Westbrook, P. R., & Keenan, S. (1986). Guidelines for the multiple sleep latency test (MSLT): A standard measure of sleepiness. Sleep, 9, 519–524.Google Scholar
  30. 30.
    Richardson, G. S., Carskadon, M. A., Flagg, W., Van den Hoed, J., Dement, W. C., & Mitler, M. M. (1978). Excessive daytime sleepiness in man: Multiple sleep latency measurement in narcoleptic and control subjects. Electroencephalography and Clinical Neurophysiology, 45, 621–627.CrossRefGoogle Scholar
  31. 31.
    Thorpy, M. J., Westbrook, P., Ferber, R., Fredrickson, P., Mahowald, M., Perez-Guerra, F., et al. (1992). The clinical use of the multiple sleep latency test. Sleep, 15, 268–276.Google Scholar
  32. 32.
    Cohen, L. (1995). Time–frequency analysis. New Jersey: Prentice Hall Signal Processing Series.Google Scholar
  33. 33.
    Clariá, F., Vallverdú, M., Riba, J., Romero, S., Barbanoj, M. J., & Caminal, P. (2011). Characterization of the cerebral activity by time-frequency representation of evoked EEG potentials. Physiological Measurement, 32, 1327–1346.CrossRefGoogle Scholar
  34. 34.
    Abásolo, D., Hornero, R., Espino, P., Alvarez, D., & Poza, J. (2006). Entropy analysis of the EEG background activity in Alzheimer’s disease patients. Physiological Measurement, 27, 241–253.CrossRefGoogle Scholar
  35. 35.
    Sleigh, W. J., Steyn-Ross, D. A., Steyn-Ross, M. L., Grant, C., & Ludbrook, G. (2004). Cortical entropy changes with general anaesthesia: Theory and experiment. Physiological Measurement, 25, 921–934.CrossRefGoogle Scholar
  36. 36.
    McCullagh, P., & Nelder, J. A. (1990). Generalized linear models. New York: Chapman & Hall.Google Scholar
  37. 37.
    De Gennaro, L., Ferrara, M., & Bertini, M. (2001). The boundary between wakefulness and sleep: quantitative electroencephalographic changes during the sleep onset period. Neuroscience, 107, 1–11.CrossRefGoogle Scholar
  38. 38.
    Iber, C., Ancoli-Israel, S., Chesson, A. L. J., & Quan, S. F. (2007). The AASM manual for the scoring of sleep and associated events. Westchester: American Academy of Sleep Medicine.Google Scholar
  39. 39.
    Inouye, T., Shinosaki, K., Sakamoto, H., Toi, S., Ukai, S., Iyama, A., et al. (1991). Quantification of EEG irregularity by use of the entropy of the power spectrum. Electroencephalography Clinical Neurophysiology, 79, 204–210.CrossRefGoogle Scholar
  40. 40.
    Fell, J., Röschke, J., Mann, K., & Schäffner, C. (1996). Discrimination of sleep stages: a comparison between spectral and nonlinear EEG measures. Electroencephalography Clinical Neurophysiology, 98, 401–410.CrossRefGoogle Scholar
  41. 41.
    Picot, A., Charbonnier, S., & Caplier, A. (2009). Monitoring drowsiness on-line using a single encephalographic channel. In C. A. B. de Mello (Ed.), Biomedical Engineering (pp. 145–164). Croatia: In Tech.Google Scholar
  42. 42.
    Garcés Correa, A., Orosco, L., & Laciar, E. (2014). Automatic detection of drowsiness in EEG records based on multimodal analysis. Medical Engineering Physics, 2, 244–249.CrossRefGoogle Scholar

Copyright information

© Taiwanese Society of Biomedical Engineering 2015

Authors and Affiliations

  • Umberto Melia
    • 1
    • 12
    • 13
  • Marc Guaita
    • 2
    • 4
  • Montserrat Vallverdú
    • 1
    • 12
    • 13
  • Francesc Clariá
    • 3
  • Josep M. Montserrat
    • 2
    • 5
    • 7
    • 11
  • Isabel Vilaseca
    • 2
    • 5
    • 6
    • 11
  • Manel Salamero
    • 2
    • 4
    • 8
    • 11
  • Carles Gaig
    • 2
    • 9
    • 10
  • Pere Caminal
    • 1
    • 12
    • 13
  • Joan Santamaria
    • 2
    • 9
    • 10
    • 11
  1. 1.Department of ESAIIUniversitat Politècnica de CatalunyaBarcelonaSpain
  2. 2.Multidisciplinary Sleep Disorders UnitHospital Clinic de BarcelonaBarcelonaSpain
  3. 3.Department of IIELleida UniversityLleidaSpain
  4. 4.Institut d’Investigació Biomèdica August Pi i Sunyer (IDIBAPS)BarcelonaSpain
  5. 5.Ciber Enfermedades Respiratorias (CIBERES)MadridSpain
  6. 6.Department of OtorhinolaryngologyHospital Clinic de BarcelonaBarcelonaSpain
  7. 7.Department of PneumologyHospital Clinic de BarcelonaBarcelonaSpain
  8. 8.Department of PsychiatryHospital Clinic de BarcelonaBarcelonaSpain
  9. 9.Department of NeurologyHospital Clinic de BarcelonaBarcelonaSpain
  10. 10.Ciber Enfermedades Neurológicas (CIBERNED)BarcelonaSpain
  11. 11.Medical SchoolUniversity of BarcelonaBarcelonaSpain
  12. 12.Centre for Biomedical Engineering ResearchBarcelonaSpain
  13. 13.CIBER of Bioengineering, Biomaterials and NanomedicineBarcelonaSpain

Personalised recommendations