Roshan Joy Martis

Automated EEG analysis of epilepsy: A review

Epilepsy is an electrophysiological disorder of the brain, characterized by recurrent seizures. Electroencephalogram (EEG) is a test that measures and records the electrical activity of the brain, and is widely used in the detection and analysis of epileptic seizures. However, it is often difficult to identify subtle but critical changes in the EEG waveform by visual inspection, thus opening up a vast research area for biomedical engineers to develop and implement several intelligent algorithms for the identification of such subtle changes. Moreover, the EEG signals are nonlinear and non-stationary in nature, which contribute to further complexities related to their manual interpretation and detection of normal and abnormal (interictal and ictal) activities. Hence, it is necessary to develop a Computer Aided Diagnostic (CAD) system to automatically identify the normal and abnormal activities using minimum number of highly discriminating features in classifiers. It has been found that nonlinear features are able to capture the complex physiological phenomena such as abrupt transitions and chaotic behavior in the EEG signals. In this review, we discuss various feature extraction methods and the results of different automated epilepsy stage detection techniques in detail. We also briefly present the various open ended challenges that need to be addressed before a CAD based epilepsy detection system can be set-up in a clinical setting.

ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform

Abstract Electrocardiogram (ECG) is the P-QRS-T wave, representing the cardiac function. The information concealed in the ECG signal is useful in detecting the disease afflicting the heart. It is very difficult to identify the subtle changes in the ECG in time and frequency domains. The Discrete Wavelet Transform (DWT) can provide good time and frequency resolutions and is able to decipher the hidden complexities in the ECG. In this study, five types of beat classes of arrhythmia as recommended by Association for Advancement of Medical Instrumentation (AAMI) were analyzed namely: non-ectopic beats, supra-ventricular ectopic beats, ventricular ectopic beats, fusion betas and unclassifiable and paced beats. Three dimensionality reduction algorithms; Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA) were independently applied on DWT sub bands for dimensionality reduction. These dimensionality reduced features were fed to the Support Vector Machine (SVM), neural network (NN) and probabilistic neural network (PNN) classifiers for automated diagnosis. ICA features in combination with PNN with spread value ( σ ) of 0.03 performed better than the PCA and LDA. It has yielded an average sensitivity, specificity, positive predictive value (PPV) and accuracy of 99.97%, 99.83%, 99.21% and 99.28% respectively using ten-fold cross validation scheme.

Automated diagnosis of Coronary Artery Disease affected patients using LDA, PCA, ICA and Discrete Wavelet Transform

Coronary Artery Disease (CAD) is the narrowing of the blood vessels that supply blood and oxygen to the heart. Electrocardiogram (ECG) is an important cardiac signal representing the sum total of millions of cardiac cell depolarization potentials. It contains important insights into the state of health and nature of the disease afflicting the heart. However, it is very difficult to perceive the subtle changes in ECG signals which indicate a particular type of cardiac abnormality. Hence, we have used the heart rate signals from the ECG for the diagnosis of cardiac health. In this work, we propose a methodology for the automatic detection of normal and Coronary Artery Disease conditions using heart rate signals. The heart rate signals are decomposed into frequency sub-bands using Discrete Wavelet Transform (DWT). Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA) were applied on the set of DWT coefficients extracted from particular sub-bands in order to reduce the data dimension. The selected sets of features were fed into four different classifiers: Support Vector Machine (SVM), Gaussian Mixture Model (GMM), Probabilistic Neural Network (PNN) and K-Nearest Neighbor (KNN). Our results showed that the ICA coupled with GMM classifier combination resulted in highest accuracy of 96.8%, sensitivity of 100% and specificity of 93.7% compared to other data reduction techniques (PCA and LDA) and classifiers. Overall, compared to previous techniques, our proposed strategy is more suitable for diagnosis of CAD with higher accuracy.

APPLICATION OF EMPIRICAL MODE DECOMPOSITION (EMD) FOR AUTOMATED DETECTION OF EPILEPSY USING EEG SIGNALS

Epilepsy is a global disease with considerable incidence due to recurrent unprovoked seizures. These seizures can be noninvasively diagnosed using electroencephalogram (EEG), a measure of neuronal electrical activity in brain recorded along scalp. EEG is highly nonlinear, nonstationary and non-Gaussian in nature. Nonlinear adaptive models such as empirical mode decomposition (EMD) provide intuitive understanding of information present in these signals. In this study a novel methodology is proposed to automatically classify EEG of normal, inter-ictal and ictal subjects using EMD decomposition. EEG decomposition using EMD yields few intrinsic mode functions (IMF), which are amplitude and frequency modulated (AM and FM) waves. Hilbert transform of these IMF provides AM and FM frequencies. Features such as spectral peaks, spectral entropy and spectral energy in each IMF are extracted and fed to decision tree classifier for automated diagnosis. In this work, we have compared the performance of classification using two types of decision trees (i) classification and regression tree (CART) and (ii) C4.5. We have obtained the highest average accuracy of 95.33%, average sensitivity of 98%, and average specificity of 97% using C4.5 decision tree classifier. The developed methodology is ready for clinical validation on large databases and can be deployed for mass screening.

Application of principal component analysis to ECG signals for automated diagnosis of cardiac health

Electrocardiogram (ECG) is the P, QRS, T wave indicating the electrical activity of the heart. The subtle changes in amplitude and duration of ECG cannot be deciphered precisely by the naked eye, hence imposing the need for a computer assisted diagnosis tool. In this paper we have automatically classified five types of ECG beats of MIT-BIH arrhythmia database. The five types of beats are Normal (N), Right Bundle Branch Block (RBBB), Left Bundle Branch Block (LBBB), Atrial Premature Contraction (APC) and Ventricular Premature Contraction (VPC). In this work, we have compared the performances of three approaches. The first approach uses principal components of segmented ECG beats, the second approach uses principal components of error signals of linear prediction model, whereas the third approach uses principal components of Discrete Wavelet Transform (DWT) coefficients as features. These features from three approaches were independently classified using feed forward neural network (NN) and Least Square-Support Vector Machine (LS-SVM). We have obtained the highest accuracy using the first approach using principal components of segmented ECG beats with average sensitivity of 99.90%, specificity of 99.10%, PPV of 99.61% and classification accuracy of 98.11%. The system developed is clinically ready to deploy for mass screening programs.

Current methods in electrocardiogram characterization.

The Electrocardiogram (ECG) is the P-QRS-T wave depicting the cardiac activity of the heart. The subtle changes in the electric potential patterns of repolarization and depolarization are indicative of the disease afflicting the patient. These clinical time domain features of the ECG waveform can be used in cardiac health diagnosis. Due to the presence of noise and minute morphological parameter values, it is very difficult to identify the ECG classes accurately by the naked eye. Various computer aided cardiac diagnosis (CACD) systems, analysis methods, challenges addressed and the future of cardiovascular disease screening are reviewed in this paper. Methods developed for time domain, frequency transform domain, and time-frequency domain analysis, such as the wavelet transform, cannot by themselves represent the inherent distinguishing features accurately. Hence, nonlinear methods which can capture the small variations in the ECG signal and provide improved accuracy in the presence of noise are discussed in greater detail in this review. A CACD system exploiting these nonlinear features can help clinicians to diagnose cardiovascular disease more accurately.

Linear and nonlinear analysis of normal and CAD-affected heart rate signals

Coronary artery disease (CAD) is one of the dangerous cardiac disease, often may lead to sudden cardiac death. It is difficult to diagnose CAD by manual inspection of electrocardiogram (ECG) signals. To automate this detection task, in this study, we extracted the heart rate (HR) from the ECG signals and used them as base signal for further analysis. We then analyzed the HR signals of both normal and CAD subjects using (i) time domain, (ii) frequency domain and (iii) nonlinear techniques. The following are the nonlinear methods that were used in this work: Poincare plots, Recurrence Quantification Analysis (RQA) parameters, Shannon entropy, Approximate Entropy (ApEn), Sample Entropy (SampEn), Higher Order Spectra (HOS) methods, Detrended Fluctuation Analysis (DFA), Empirical Mode Decomposition (EMD), Cumulants, and Correlation Dimension. As a result of the analysis, we present unique recurrence, Poincare and HOS plots for normal and CAD subjects. We have also observed significant variations in the range of these features with respect to normal and CAD classes, and have presented the same in this paper. We found that the RQA parameters were higher for CAD subjects indicating more rhythm. Since the activity of CAD subjects is less, similar signal patterns repeat more frequently compared to the normal subjects. The entropy based parameters, ApEn and SampEn, are lower for CAD subjects indicating lower entropy (less activity due to impairment) for CAD. Almost all HOS parameters showed higher values for the CAD group, indicating the presence of higher frequency content in the CAD signals. Thus, our study provides a deep insight into how such nonlinear features could be exploited to effectively and reliably detect the presence of CAD.

Cardiac decision making using higher order spectra

Abstract The electrocardiogram (ECG) is the P-QRS-T wave representing the information about the condition of the heart. The shape and size of the ECG signal may contain useful information about the nature of disease afflicting the heart. However, these subtle details cannot be directly monitored by the human eye and may indicate a particular cardiac abnormality. Also, the ECG is highly subjective, the symptoms may appear at random in the time scale. Hence computer assisted methods can help physicians to monitor cardiac health easily and accurately. The ECG signal is nonlinear and non-stationary in nature. These subtle variations can be captured using non-linear dynamical Higher Order Statistics (HOS) techniques. Bispectrum is the third order spectra which captures information beyond mean and standard deviation. In this work we have analyzed five types of beats namely: Normal, Right Bundle Branch Block (RBBB), Left Bundle Branch Block (LBBB), Atrial Premature Contraction (APC) and Ventricular Premature Contraction (VPC). The extracted bispectrum features are subjected to principal component analysis (PCA) for dimensionality reduction. These principal components were fed to four layered feed forward neural network and Least Square-Support Vector Machine (LS-SVM) for automated pattern identification. In our work, we have obtained highest average accuracy of 93.48%, average sensitivity and specificity of 99.27% and 98.31% respectively using LS-SVM with Radial Basis Function (RBF) kernel. Our system is clinically ready to run on large amount of data sets.

Automated diagnosis of epilepsy using CWT, HOS and texture parameters.

Epilepsy is a chronic brain disorder which manifests as recurrent seizures. Electroencephalogram (EEG) signals are generally analyzed to study the characteristics of epileptic seizures. In this work, we propose a method for the automated classification of EEG signals into normal, interictal and ictal classes using Continuous Wavelet Transform (CWT), Higher Order Spectra (HOS) and textures. First the CWT plot was obtained for the EEG signals and then the HOS and texture features were extracted from these plots. Then the statistically significant features were fed to four classifiers namely Decision Tree (DT), K-Nearest Neighbor (KNN), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) to select the best classifier. We observed that the SVM classifier with Radial Basis Function (RBF) kernel function yielded the best results with an average accuracy of 96%, average sensitivity of 96.9% and average specificity of 97% for 23.6 s duration of EEG data. Our proposed technique can be used as an automatic seizure monitoring software. It can also assist the doctors to cross check the efficacy of their prescribed drugs.

A two-stage mechanism for registration and classification of ECG using Gaussian mixture model

An automatic classifier for electrocardiogram (ECG) based cardiac abnormality detection using Gaussian mixture model (GMM) is presented here. In first stage, pre-processing that includes re-sampling, QRS detection, linear prediction (LP) model estimation, residual error signal computation and principal component analysis (PCA) has been used for registration of linearly independent ECG features. GMM is here used for classification based on the registered features in a two-class pattern classification problem using 730 ECG segments from MIT-BIH Arrhythmia and European ST-T Ischemia datasets. A set of 12 features explaining 99.7% of the data variability is obtained using PCA from residual error signals for GMM based classification. Sixty percent of the data is used for training the classifier and 40% for validating. It is observed that the overall accuracy of the proposed strategy is 94.29%. As an advantage, it is also verified that Chernoff bound and Bhattacharya bounds lead to minimum error for GMM based classifier. In addition, a comparative study is done with the standard classification techniques with respect to its overall accuracy.