Backpropagation Artificial Neural Network Detects Changes in Electro-Encephalogram Power Spectra of Syncopic Patients

This paper presents an effective application of backpropagation artificial neural network (ANN) in differentiating electroencephalogram (EEG) power spectra of syncopic and normal subjects. Digitized 8-channel EEG data were recorded with standard electrodes placement and amplifier settings from five confirmed syncopic and five normal subjects. The preprocessed EEG signals were fragmented in two-second artifact free epochs for calculation and analysis of changes due to syncope. The results revealed significant increase in percentage δ and α (p<0.5 or better) with significant reduction in percentage θ activity (p<0.05). The backpropagation ANN used for classification contains 60 nodes in input layer, weighted from power spectrum data from 0 to 30 Hz, 18 nodes in hidden layer and an output node. The ANN was found effective in differentiating the EEG power spectra from syncopic EEG power spectra and the normal EEG power spectra with an accuracy of 88.87% (85.75% for syncopic and 92% for normal).

[1]  H A al-Nashash,et al.  A dynamic Fourier series for the compression of ECG using FFT and adaptive coefficient estimation. , 1995, Medical engineering & physics.

[2]  V Kumar,et al.  Diagnostic acceptability of FFT-based ECG data compression. , 1997, Journal of medical engineering & technology.

[3]  B. W. Jervis,et al.  Spectral analysis of EEG responses , 1989, Medical and Biological Engineering and Computing.

[4]  Samir Karia,et al.  Head up tilt test in the diagnosis of neurocardiogenic syncope in childhood and adolescence. , 2004, Neurology India.

[5]  N. Thakor,et al.  Dominant frequency analysis of EEG reveals brain's response during injury and recovery , 1996, IEEE Transactions on Biomedical Engineering.

[6]  F. Ashtari,et al.  A Study of the Relationship between Syncope Attacks and Diminished Carotid and Vertebral Artery Flow Using Doppler Ultrasonography of Cervical Vessels , 2005 .

[7]  I. Figueira,et al.  Inferences from a community study about non-epileptic events. , 2002, Arquivos de neuro-psiquiatria.

[8]  R. Adams,et al.  Principles of Neurology , 1996 .

[9]  F. Freemon,et al.  Electroencephalography should not be routine in the evaluation of syncope in adults. , 1990, Archives of internal medicine.

[10]  D. Kosinski,et al.  Neurally mediated syncope with an update on indications and usefulness of head-upright tilt table testing and pharmacologic therapy. , 1994, Current opinion in cardiology.

[11]  R. K. Sinha.  Artificial neural network detects changes in electro-encephalogram power spectrum of different sleep-wake states in an animal model of heat stress , 2003, Medical and Biological Engineering and Computing.

[12]  N V Thakor,et al.  Quantitative EEG during Early Recovery from Hypoxic-Ischemic Injury in Immature Piglets: Burst Occurrence and Duration , 1999, Clinical EEG.

[13]  R. Sheldon,et al.  Usefulness of clinical factors in predicting outcomes of passive tilt tests in patients with syncope. , 2000, The American journal of cardiology.

[14]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[15]  R. K. Sinha.  Electro-encephalogram disturbances in different sleep-wake states following exposure to high environmental heat , 2004, Medical and Biological Engineering and Computing.

[16]  Valluru Rao,et al.  C++ neural networks and fuzzy logic , 1993 .

[17]  W. Kapoor,et al.  CLINICAL GUIDELINE: Diagnosing Syncope: Part 1: Value of History, Physical Examination, and Electrocardiography , 1997, Annals of Internal Medicine.

[18]  M. Lamarre-Cliche,et al.  The fainting patient: value of the head-upright tilt-table test in adult patients with orthostatic intolerance. , 2001, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[19]  S. Sarbadhikari.  A neural network confirms that physical exercise reverses EEG changes in depressed rats. , 1995, Medical engineering & physics.

[20]  H. Lagercrantz,et al.  Heart rate response profiles during head upright tilt test in infants with apparent life threatening events , 1997, Archives of disease in childhood.

[21]  N. Thakor,et al.  Time-Dependent Entropy Estimation of EEG Rhythm Changes Following Brain Ischemia , 2003, Annals of Biomedical Engineering.

[22]  A. Ray,et al.  Chronic exercise alters EEG power spectra in an animal model of depression. , 1996, Indian journal of physiology and pharmacology.

[23]  N. Thakor,et al.  Vulnerability of the thalamic somatosensory pathway after prolonged global hypoxic–ischemic injury , 2002, Neuroscience.

[24]  B G White,et al.  Electroencephalographic changes during whole body hyperthermia in humans. , 1980, Electroencephalography and clinical neurophysiology.

[25]  P. Marche,et al.  Automated neural network detection of wavelet preprocessed electrocardiogram late potentials , 2006, Medical and Biological Engineering and Computing.

[26]  H. Lüders,et al.  Interobserver variability in EEG interpretation , 1985, Neurology.

[27]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.