An artificial intelligence approach to classify and analyse EEG traces

We present a fully automatic system for the classification and analysis of adult electroencephalograms (EEGs). The system is based on an artificial neural network which classifies the single epochs of trace, and on an Expert System (ES) which studies the time and space correlation among the outputs of the neural network; compiling a final report. On the last 2000 EEGs representing different kinds of alterations according to clinical occurrences, the system was able to produce 80% good or very good final comments and 18% sufficient comments, which represent the documents delivered to the patient. In the remaining 2% the automatic comment needed some modifications prior to be presented to the patient. No clinical false-negative classifications did arise, i.e. no altered traces were classified as 'normal' by the neural network. The analysis method we describe is based on the interpretation of objective measures performed on the trace. It can improve the quality and reliability of the EEG exam and appears useful for the EEG medical reports although it cannot totally substitute the medical doctor who should now read the automatic EEG analysis in light of the patient's history and age.

[1]  Lionel Tarassenko,et al.  Clinical applications of artificial neural networks: Neural network analysis of sleep disorders , 2001 .

[2]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[3]  Donald C. Wunsch,et al.  Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG , 2000, Neurocomputing.

[4]  B.H. Jansen,et al.  Knowledge-based approach to sleep EEG analysis-a feasibility study , 1989, IEEE Transactions on Biomedical Engineering.

[5]  Steven Kay,et al.  Modern Spectral Estimation: Theory and Application , 1988 .

[6]  W. M. Carey,et al.  Digital spectral analysis: with applications , 1986 .

[7]  Jose C. Principe,et al.  An Expert System Architecture For Abnormal EEG Discrimination , 1990, [1990] Proceedings of the Twelfth Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[8]  I. Rezek,et al.  Stochastic complexity measures for physiological signal analysis , 1998, IEEE Transactions on Biomedical Engineering.

[9]  Gert Pfurtscheller,et al.  Considerations on Adaptive Autoregressive Modelling in EEG Analysis , 1998 .

[10]  Masami Ito,et al.  Task decomposition and module combination based on class relations: a modular neural network for pattern classification , 1999, IEEE Trans. Neural Networks.

[11]  Mingui Sun,et al.  A neural network system for automatic classification of sleep stages , 1993, [1993] Proceedings of the Twelfth Southern Biomedical Engineering Conference.

[12]  Emmanuel Ifeachor,et al.  Intelligent artefact identification in electroencephalography signal processing , 1997 .

[13]  R. Schiffer,et al.  Recurrent neural network-based approach for early recognition of Alzheimer's disease in EEG , 2001, Clinical Neurophysiology.

[14]  Stephen J. Roberts,et al.  A Probabilistic Approach to High-Resolution Sleep Analysis , 2001, ICANN.

[15]  B H Jansen,et al.  K-complex detection using multi-layer perceptrons and recurrent networks. , 1994, International journal of bio-medical computing.

[16]  B.H. Jansen.  Artificial neural nets for K-complex detection , 1990, IEEE Engineering in Medicine and Biology Magazine.

[17]  David Sommer,et al.  Clustering of EEG-Segments Using Hierarchical Agglomerative Methods and Self-Organizing Maps , 2001, ICANN.

[18]  I. Bankman,et al.  Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks , 1992, IEEE Transactions on Biomedical Engineering.

[19]  Hsiao-Wen Chung,et al.  An EEG spike detection algorithm using artificial neural network with multi-channel correlation , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[20]  Richard Dybowski,et al.  Clinical applications of artificial neural networks: Theory , 2001 .

[21]  Ah Chung Tsoi,et al.  Classification of Electroencephalogram Using Artificial Neural Networks , 1993, NIPS.

[22]  Bao-Liang Lu,et al.  Massively Parallel Classification of EEG Signals Using Min-Max Modular Neural Networks , 2001, ICANN.