http://iet.metastore.ingenta.com
1887

Identification of inter-ictal spikes in the EEG using neural network analysis

Identification of inter-ictal spikes in the EEG using neural network analysis

For access to this article, please select a purchase option:

Buy article PDF
$19.95
(plus tax if applicable)
Buy Knowledge Pack
10 articles for $120.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IEE Proceedings - Science, Measurement and Technology — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Between seizures, the electroencephalogram (EEG) of subjects who suffer from epilepsy is usually characterised by occasional spikes or spike and wave complexes (inter-ictal activity). These are notoriously difficult to detect reliably, and they are occasionally missed by the clinicians who review the paper records retrospectively. The authors investigate the training and testing of a neural network classifier for the detection of inter-ictal spikes in these subjects. For the characterisation of the EEG signal, they consider both time-domain parameters normalised with respect to context and coefficients from an autoregressive model. It is shown how to use balanced databases to evaluate the discriminatory power of these parameters when they are used as the input features to a multi-layer perceptron (MLP). Both patient-specific classifiers and a generic system tested on independent test subjects are investigated. With the former, spikes are detected with an accuracy varying from 85.6% to 95.6%, a sensitivity varying from 83.1% to 97.3% and a specificity varying from 85.9% to 95.5%. The performance of the generic MLP system is not substantially degraded with respect to this, but there are too many false positives for the system to be considered for regular clinical use at the moment. The authors suggest how this problem might be solved using a combination of techniques.

References

    1. 1)
      • S.J. Roberts , L. Tarassenko . Analysis of the sleep EEG using a multilayernetwork with spatial organisation. IEE Proc.-F, Radar Signal Process. , 420 - 425
    2. 2)
      • S.J. Roberts , L. Tarassenko , A.F. Murray . (1995) Automated sleep EEG analysis using an RBF network, Applications of neural networks.
    3. 3)
      • J. Pardey , S.J. Roberts , L. Tarassenko , J. Stradling . A new approach to the analysis of the human sleep/wakefulness continuum. J. Sleep Research , 4 , 201 - 210
    4. 4)
      • J.R. Stradling , J. Partlett , R.J.O. Davies , D. Siegwart , L. Tarassenko . Effect of short term graded withdrawal of nasal continuous positive airwaypressureon systemic blood pressure in patients with obstructive sleep apnoea. Blood Pressure , 234 - 240
    5. 5)
      • R.J.O. Davies , L.S. Bennett , C. Barbour , L. Tarassenko , J.R. Stradling . Second by second patterns in cortical electroencephalograph and sub-cortical,systolic blood pressure, arousal during Cheyne–Stokes breathing. Eur. Resp. J
    6. 6)
      • C.A. Espie , A. Paul , J. McFie , P. Amos , D. Hamilton , J.H. McColl , L. Tarassenko , J. Pardey . Sleep studies of adults with severe or profound mental retardation andepilepsy. Am. J. Ment. Retard. , 47 - 59
    7. 7)
      • J.R. Hughes . (1994) EEG in clinical practice.
    8. 8)
      • J. Gotman , P. Gloor . Automatic recognition and quantification of interictalepileptic activity in the human scalp EEG. Electroencephalogr. Clin. Neurophysiol. , 513 - 529
    9. 9)
      • J.R. Glover , P.Y. Ktonas , J.D. Frost . Context based automated detectionof epileptogenic sharp transients in the EEG: elimination of false positives. IEEE Trans. Biomed. Eng. , 519 - 527
    10. 10)
      • T. Pietila , S. Vafaakoski , U. Nousiainen , A. Varri , H. Frey , V. Hakkinen , Y. Neuvo . Evaluation of a computerized system for recognition of epilepticactivity during long-term EEG recording. Electroencephalog. Clin. Neurophysiol. , 438 - 443
    11. 11)
      • L. Tarassenko . (1998) A guide to neural computing applications.
    12. 12)
      • J. Pardey , S. Roberts , L. Tarassenko . A review of parametric modellingtechniques for EEG analysis. Med. Eng. Phys. , 2 - 11
    13. 13)
      • W.R.S. Webber , B. Litt , K. Wilson , R.P. Lesser . Practical detectionof epileptiform discharges (EDs) in the EEG using an artificial neural network: a comparisonof raw and parameterized EEG data. Electroencephalog. Clin. Neurophysiol. , 194 - 204
    14. 14)
      • B. Hjorth . The physical significance of time domain descriptors in EEG analysis. Electroencephalogr. Clin. Neurophysiol. , 306 - 310
    15. 15)
      • M. Walmsley . On the normalised slope descriptor method of quantifying EEG. IEEE Trans. Biomed. Eng. , 720 - 723
    16. 16)
      • Saltzberg, B., Heath, R.G., Edwards, R.J.: `EEG spike detection in schizophrenia research', Digest of the 7th international conference Medical and biologicalengineering, 1967, Stockholm, p. 266.
    17. 17)
      • D.O. Walter , H.F. Muller , R.M. Jell . Semiautomatic quantification ofsharpness of EEG phenomena. IEEE Trans. Biomed. Eng. , 53 - 54
    18. 18)
      • J.R. Smith . Automatic analysis and detection of EEG spikes. IEEE Trans. Biomed. Eng. , 1 - 7
    19. 19)
      • J.R. Carrie . A technique for analysing transient EEG abnormalities. Electroencephalogr. Clin. Neurophysiol. , 199 - 201
    20. 20)
      • Khan, Y.U.: `Detection of epileptic events in electroencephalograms using artificialneural networks', 1997, DPhil, Oxford University.
    21. 21)
      • J. Gotman . Automatic recognition of interictal spikes. Electroencephalogr. Clin. Neurophysiol. , 93 - 114
    22. 22)
      • K. Fukunaga . (1991) Introduction to statistical pattern recognition.
    23. 23)
      • A. Cohen . (1986) Biomedical signal processing.
    24. 24)
      • E.B. Baum , D. Haussler . What size net gives valid generalization. Neur. Comp. , 151 - 160
    25. 25)
      • Holt, M.R.G.: `The use of neural networks in the analysis of the anaesthetic electroencephalogram', 1997, DPhil, Oxford University.
    26. 26)
      • M.R.G. Holt , M. Tooley , F. Forest , C. Prys-Roberts , L. Tarassenko . The use of parametric modelling and statistical pattern recognition inthe detectionof awareness during general anaesthesia.
    27. 27)
      • C.M. Bishop . (1995) Neural networks for pattern recognition.
    28. 28)
      • A.J. Bell , T.J. Sejnowski . An information-maximisation approach to blindseparation and blind deconvolution. Neur. Comp. , 1129 - 1159
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-smt_19982328
Loading

Related content

content/journals/10.1049/ip-smt_19982328
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address