Automated seizure detection using limited-channel EEG and non-linear dimension reduction

Electroencephalography (EEG) is an essential component in evaluation of epilepsy. However, full-channel EEG signals recorded from 18 to 23 electrodes on the scalp is neither wearable nor computationally effective. This paper presents advantages of both channel selection and nonlinear dimension reduction for accurate automatic seizure detection. We first extract the frequency domain features from the full-channel EEG signals. Then, we use a random forest algorithm to determine which channels contribute the most in discriminating seizure from non-seizure events. Next, we apply a non-linear dimension reduction technique to capture the relationship among data elements and map them in low dimension. Finally, we apply a KNN classifier technique to discriminate between seizure and non-seizure events. The experimental results for 23 patients show that our proposed approach outperforms other techniques in terms of accuracy. It also visualizes long-term data in 2D to enhance physician cognition of occurrence and disease progression.

[1]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[2]  George Atia,et al.  Randomized Robust Subspace Recovery and Outlier Detection for High Dimensional Data Matrices , 2015, IEEE Transactions on Signal Processing.

[3]  Javad Birjandtalab,et al.  Unsupervised EEG analysis for automated epileptic seizure detection , 2016, International Workshop on Pattern Recognition.

[4]  Malek Adjouadi,et al.  Connectivity maps of different types of epileptogenic patterns , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[5]  Erchin Serpedin,et al.  Channel selection and feature enhancement for improved epileptic seizure onset detector , 2014 .

[6]  Hassan Ghasemzadeh,et al.  An Energy-Efficient Computational Model for Uncertainty Management in Dynamically Changing Networked Wearables , 2016, ISLPED.

[7]  Emma K. T. Benn,et al.  SUDEP: What Are the Risk Factors? Do Seizures or Antiepileptic Drugs Contribute to an Increased Risk? , 2012 .

[8]  W. Tatum.  Ellen R. Grass Lecture: Extraordinary EEG , 2014, The Neurodiagnostic journal.

[9]  Mehrdad Nourani,et al.  Multi-Biosignal Analysis for Epileptic Seizure Monitoring , 2017, Int. J. Neural Syst..

[10]  Yang Cheng,et al.  Categorical Analysis of Human T Cell Heterogeneity with One-Dimensional Soli-Expression by Nonlinear Stochastic Embedding , 2016, The Journal of Immunology.

[11]  J D Norrie,et al.  Patterns of treatment response in newly diagnosed epilepsy , 2012, Neurology.

[12]  Michel Verleysen,et al.  Quality assessment of nonlinear dimensionality reduction based on K-ary neighborhoods , 2008, FSDM.

[13]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[14]  Michael Chen,et al.  Semi-automated patient-specific scalp EEG seizure detection with unsupervised machine learning , 2015, 2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB).

[15]  Nanda Kambhatla,et al.  Dimension Reduction by Local Principal Component Analysis , 1997, Neural Computation.

[16]  George Atia,et al.  A Subspace Learning Approach for High Dimensional Matrix Decomposition with Efficient Column/Row Sampling , 2016, ICML.

[17]  R. E. Madsen,et al.  Channel selection for automatic seizure detection , 2012, Clinical Neurophysiology.

[18]  Mehrdad Nourani,et al.  Nonlinear dimension reduction for EEG-based epileptic seizure detection , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[19]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[20]  Michel Verleysen,et al.  Nonlinear Dimensionality Reduction , 2021, Computer Vision.

[21]  Hojjat Adeli,et al.  A Wavelet-Chaos Methodology for Analysis of EEGs and EEG Subbands to Detect Seizure and Epilepsy , 2007, IEEE Transactions on Biomedical Engineering.

[22]  Miron B. Kursa,et al.  Robustness of Random Forest-based gene selection methods , 2013, BMC Bioinformatics.

[23]  Fathi E. Abd El-Samie,et al.  A review of channel selection algorithms for EEG signal processing , 2015, EURASIP Journal on Advances in Signal Processing.

[24]  A. Malani,et al.  Initial management of epilepsy. , 2008, The New England journal of medicine.

[25]  Keinosuke Fukunaga,et al.  A Branch and Bound Algorithm for Feature Subset Selection , 1977, IEEE Transactions on Computers.

[26]  Erhan Bergil,et al.  The Investigation of Channel Selection Effects on Epileptic Analysis of EEG Signals , 2015 .

[27]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[28]  Ali H. Shoeb,et al.  Application of machine learning to epileptic seizure onset detection and treatment , 2009 .

[29]  Chun-An Chou,et al.  A Simple Distance Based Seizure Onset Detection Algorithm Using Common Spatial Patterns , 2016, BIH.

[30]  Rebecca Hiscott.  News from the American Epilepsy Society Annual Meeting: Researchers Develop Wearable EEG Device to Record Seizure Activity , 2015 .

[31]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[32]  R. Dahlhaus.  On the Kullback-Leibler information divergence of locally stationary processes , 1996 .

[33]  C. M. Michel,et al.  Temporal and spatial determination of EEG-seizure onset in the frequency domain , 2000, Clinical Neurophysiology.

[34]  Sean C. Bendall,et al.  viSNE enables visualization of high dimensional single-cell data and reveals phenotypic heterogeneity of leukemia , 2013, Nature Biotechnology.