Application of Classical and Model-Based Spectral Methods to Describe the State of Alertness in EEG

Electrophysiological recordings are considered a reliable method of assessing a person's alertness. Sleep medicine is asked to offer objective methods to measure daytime alertness, tiredness and sleepiness. In this study, EEG signals recorded from 30 subjects were processed by PC-computer using classical and model-based methods. The classical method (fast Fourier transform) and three model-based methods (Burg autoregresse, moving average, least-squares modified Yule–Walker autoregressive moving average methods) were selected for processing EEG signals to discriminate the alertness level of subject. Power spectra of EEG signals were obtained by using these spectrum analysis techniques. These EEG spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of vigilance state of subject. It is found that, FFT and MA methods have low spectral resolution, these two methods are not appropriate for the analysis of the a wake–sleep correlation. Burg AR and least-squares modified Yule–Walker ARMA methods' performance characteristics have been found extremely valuable for the determination of vigilance state of a healthy subject, because of their clear spectra.     

AR Spectral Analysis Technique for Human PPG,ECG and EEG Signals

In this study, Fast Fourier transform (FFT) and autoregressive (AR) methods were selected for processing the photoplethysmogram (PPG), electrocardiogram (ECG), electroencephalogram (EEG) signals recorded in order to examine the effects of pulsed electromagnetic field (PEMF) at extremely low frequency (ELF) upon the human electrophysiological signal behavior. The parameters in the autoregressive (AR) method were found by using the least squares method. The power spectra of the PPG, ECG, and EEG signals were obtained by using these spectral analysis techniques. These power spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in extraction of the features representing the PPG, ECG, and EEG signals. Some conclusions were drawn concerning the efficiency of the FFT and least squares AR methods as feature extraction methods used for representing the signals under study.     

Determination of stenosis and occlusion in arteries with the application of FFT,AR, and ARMA methods

Doppler ultrasound is a noninvasive technique that allows the examination of the direction, velocity, and volume of blood flow. Therefore, Doppler ultrasonography is known as reliable technique, which demonstrates the flow characteristics and resistance of arteries in various vascular disease. In this study, arterial Doppler signals recorded from 105 subjects were processed by PC-computer using fast Fourier transform, Burg autoregressive, and least squares modified Yule–Walker autoregressive moving average methods. Doppler power spectrums of arterial Doppler signals were obtained by using these spectrum analysis techniques. The variations in the shape of the Doppler power spectrums as a function of time were presented in the form of sonograms in order to obtain medical information. These sonograms were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of stenosis and occlusion in arteries. Reliable information on hemodynamic alterations in arteries can be obtained by evaluation of these sonograms.     

Application of Periodogram and AR Spectral Analysis to EEG Signals

In this study, in order to analyze the EEG signal, the conventional and modern spectral methods were investigated. Interpretation and performance of these methods were detected for clinical applications. For this purpose EEG data obtained from different persons were processed by PC computer using periodogram and AR model algorithms. Periodogram and AR modeling approaches were compared for their resolution and interpretation performance. It was determined that the AR approach is better for the use in clinical and research areas, because of the clear spectra that are obtained by it.     

Analysis of EEG Signals Under Flash Stimulation for Migraine and Epileptic Patients

Migraine and epilepsy are both persistent disorders characterised by recurrent neurological attacks. Visual symptoms and hypersensitivity to light stimuli are frequent in migraine. Analysis of EEG signals under flash stimulation for migraine and epileptic patients is not a new method. But magnitude increasing under flash stimulation for migraine patients has not been studied yet. The aims of this study is the analysis of multichannel electroencephalogram (EEG) in migraine and epileptic patients by visual evoked potentials (VEP) and investigate the existence of magnitude increasing under flash stimulation for migraine patients. In this study as a method of flash stimuli at frequencies of 2, 4 and 6 Hz were applied to different migraine and epileptic patients under pain-free phase with the EEG recorded from 18 scalp electrodes, referred to the linked earlobes. We used AR parametric method to analyze and characterize EEG signals in migraine and epileptic patients. The variations in the EEG power spectra shapes were examined in order to obtain medical information. These power spectra were then used to compare the applied method in terms of their frequency resolution and the effects in determination of migraine and epilepsy. Global performance of the proposed methods was evaluated by means of the visual inspection of power spectral densities (PSDs). For the migraine patients, an increase in amplitude has observed at the beta bands of EEG signals under flash stimulation as compared to EEG signals without stimulation. As opposed to this, for epileptic patients, an increase in amplitude has observed at the alpha bands of EEG signals without flash stimulation. Meanwhile for the control groups, there is no change between EEG signals under flash stimulation and without flash stimulation.     

Artificial Neural Network and Wavelet Based Automated Detection of Sleep Spindles, REM Sleep and Wake States

Backpropagation artificial neural network (ANN) has been designed to classify sleep–wake stages. Four hours continuous three channel polygraphic signals such as EEG (electroencephalogram), EOG (electrooculogram) and EMG (electromyogram) from conscious subjects were digitally recorded and stored in computer. EOG and EMG signals were used for manual identification of sleep states before training and testing of ANN. The percentages power of the 2 s epochs of the digitized EEG signals from each of three sleep–wake patterns, sleep spindles (SS), rapid eye movement (REM) sleep and awake (AWA) sates, were calculated and analyzed to select the manually confirmed sleep–wake states for each epoch. Further, second order Daubechies mother wavelet has been used to get the wavelet coefficients for the selected EEG epochs. The wavelet coefficients for the EEG epochs (64 data) were selected as inputs for the training the network and to classify SS, REM sleep and AWA stages. The ANN architecture used (64–14–3) in present study shows overall very good agreement with manual sleep stage scoring with an average of 95.35% for all the 1,140 samples tested from SS, REM and AWA stages. This architecture of ANN was also found effectively differentiating the EEG power spectra from different sleep–wake states (96.84% in SS, 93.68% in REM sleep, 95.52% in AWA state). The high performance observed with the system based on wavelet coefficients along with the ANN, highlights the need of this computational tool into the field of sleep research. Certificate of Originality  This is to certify that the article submitted for publication in Journal of Medical Systems has not been published, nor is being considered for publication, elsewhere.     

心搏间隔(R-R)波动的自回归模型分析

用自回归(AR)模型分析短时心血管控制系统(植物神经系统)功能的心搏间隔(R-R)波动。实验在10条草狗上进行。根据Marple的最小二乘法对R-R间隔波作AR模型分析。谱估计显示:在缺血、缺氧及失血状态时,低频段面积增加,高频段面积减少,两者的比值与对照时相比,差别有极显著意义P<0.01)。表明该方法可有效地、无创伤性地反映短时心血管控制系统的调节功能。     

Neural Networks with Periodogram and Autoregressive Spectral Analysis Methods in Detection of Epileptic Seizure

Approximately 1% of the people in the world suffer from epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. Predicting the onset of epileptic seizure is an important and difficult biomedical problem, which has attracted substantial attention of the intelligent computing community over the past two decades. The purpose of this work was to investigate the performance of the periodogram and autoregressive (AR) power spectrum methods to extract classifiable features from human electroencephalogram (EEG) by using artificial neural networks (ANN). The feedforward ANN system was trained and tested with the backpropagation algorithm using a large data set of exemplars. We present a method for the automatic comparison of epileptic seizures in EEG, allowing the grouping of seizures having similar overall patterns. Each channel of the EEG is first broken down into segments having relatively stationary characteristics. Features are then calculated for each segment, and all segments of all channels of the seizures of a patient are grouped into clusters of similar morphology. This clustering allows labeling of every EEG segment. Examples from 5 patients with scalp electrodes illustrate the ability of the method to group seizures of similar morphology. It was observed that ANN classification of EEG signals with AR preprocessing gives better results, and these results can also be used for the deduction of epileptic seizure.     

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). Certificate of Originality—This is to certify that the article submitted for publication in ‘Journal of Medical Systems’ has not been publ-ished, nor is being considered for publication, elsewhere. (Rakesh Kumar Sinha)     

Determining the Amount of Anesthetic Medicine to Be Applied by Using Elman’s Recurrent Neural Networks via Resilient Back Propagation

In this study, Elman recurrent neural networks have been defined by using conjugate gradient algorithm in order to determine the depth of anesthesia in the continuation stage of the anesthesia and to estimate the amount of medicine to be applied at that moment. The feed forward neural networks are also used for comparison. The conjugate gradient algorithm is compared with back propagation (BP) for training of the neural Networks. The applied artificial neural network is composed of three layers, namely the input layer, the hidden layer and the output layer. The nonlinear activation function sigmoid (sigmoid function) has been used in the hidden layer and the output layer. EEG data has been recorded with Nihon Kohden 9200 brand 22-channel EEG device. The international 8-channel bipolar 10–20 montage system (8 TB-b system) has been used in assembling the recording electrodes. EEG data have been recorded by being sampled once in every 2 milliseconds. The artificial neural network has been designed so as to have 60 neurons in the input layer, 30 neurons in the hidden layer and 1 neuron in the output layer. The values of the power spectral density (PSD) of 10-second EEG segments which correspond to the 1–50 Hz frequency range; the ratio of the total power of PSD values of the EEG segment at that moment in the same range to the total of PSD values of EEG segment taken prior to the anesthesia.     

Detection of Carotid Artery Disease by Using Learning Vector Quantization Neural Network

Doppler ultrasound has been usually preferred for investigation of the artery conditions in the last two decades, because it is a non-invasive, easy to apply and reliable technique. In this study, a biomedical system based on Learning Vector Quantization Neural Network (LVQ NN) has been developed in order to classify the internal carotid artery Doppler signals obtained from the 191 subjects, 136 of them had suffered from internal carotid artery stenosis and rest of them had been healthy subject. The system is composed of feature extraction and classification parts, basically. In the feature extraction stage, power spectral density (PSD) estimates of internal carotid artery Doppler signals were obtained by using Burg autoregressive (AR) spectrum analysis technique in order to obtain medical information. In the classification stage, LVQ NN was used classify features from Burg AR method. In experiments, LVQ NN based method reached 97.91% classification accuracy with 5 fold Cross Validation (CV) technique. In addition, the classification performance of the LVQ NN was compared with some methods such as Multi Layer Perceptron (MLP) NN, Naive Bayes (NB), K-Nearest Neighbor (KNN), decision tree and Support Vector Machine (SVM) with sensitivity and specificity statistical parameters. The classification results showed that the LVQ NN method is effective for classification of internal carotid artery Doppler signals.     

Application of Higher Order Spectra to Identify Epileptic EEG

Epilepsy is characterized by the spontaneous and seemingly unforeseeable occurrence of seizures, during which the perception or behavior of patients is disturbed. An automatic system that detects seizure onsets would allow patients or the people near them to take appropriate precautions, and could provide more insight into this phenomenon. Various methods have been proposed to predict the onset of seizures based on EEG recordings. The use of nonlinear features motivated by the higher order spectra (HOS) has been reported to be a promising approach to differentiate between normal, background (pre-ictal) and epileptic EEG signals. In this work, we made a comparative study of the performance of Gaussian mixture model (GMM) and Support Vector Machine (SVM) classifiers using the features derived from HOS and from the power spectrum. Results show that the selected HOS based features achieve 93.11% classification accuracy compared to 88.78% with features derived from the power spectrum for a GMM classifier. The SVM classifier achieves an improvement from 86.89% with features based on the power spectrum to 92.56% with features based on the bispectrum.     

Improving Mental Task Classification by Adding High Frequency Band Information

Features extracted from delta, theta, alpha, beta and gamma bands spanning low frequency range are commonly used to classify scalp-recorded electroencephalogram (EEG) for designing brain–computer interface (BCI) and higher frequencies are often neglected as noise. In this paper, we implemented an experimental validation to demonstrate that high frequency components could provide helpful information for improving the performance of the mental task based BCI. Electromyography (EMG) and electrooculography (EOG) artifacts were removed by using blind source separation (BSS) techniques. Frequency band powers and asymmetry ratios from the high frequency band (40–100 Hz) together with those from the lower frequency bands were used to represent EEG features. Finally, Fisher discriminant analysis (FDA) combining with Mahalanobis distance were used as the classifier. In this study, four types of classifications were performed using EEG signals recorded from four subjects during five mental tasks. We obtained significantly higher classification accuracy by adding the high frequency band features compared to using the low frequency bands alone, which demonstrated that the information in high frequency components from scalp-recorded EEG is valuable for the mental task based BCI.     

Use of Support Vector Machines and Neural Network in Diagnosis of Neuromuscular Disorders

In this study the performance of support vector machine (SVM)and back-propagation neural network were applied to analyze the classification of the electromyogram (EMG) signals obtained from normal, neuropathy and myopathy subjects. By using autoregressive (AR) modeling, AR coefficients were obtained from EMG signals. Moreover, the support vector machine and artificial neural network (ANN) were used as base classifiers. The AR coefficients were benefited as inputs for SVM and ANN. Besides, these coefficients were tested both in ANN and SVM. The results show that SVM has high anticipation level in the diagnosis of neuromuscular disorders. It is proved that its test performance is high compared with ANN.     

Visual and computer evaluation of diazepam-induced EEG changes in epilepsy for localization of epileptogenic lesion]

Diazepam-induced EEG changes were analyzed both visually and by computer in epilepsy for localization of epileptogenic lesion. The results demonstrated that changes in beta spectral were diminished in 11/24 or 15/25 cases, but regionally increased in 3/24 or 3/25 patients overlying the epileptogenic lesion or area of EEG abnormalities. Diazepam-induced delta spectral power was usually increased (9/24), but occasionally focally reduced (3/24) over the lesion. The percentage of positive findings for localization was 38% with visual analysis and 46% with spectral analysis in beta spectral power, 38% in delta spectral power, and 67% with the analysis in combined beta with delta, and 83% with four independent tests. Spectral analysis was more sensitive than visual analysis, and it was a useful supplement to visual analysis, to general EEG evaluation, and to CT. Finally, the study emphasized that a localizing diagnosis to define the epileptogenic lesion should be based on the combination of a multitude of independent tests.     

Determination of coronary failure with the application of FFT and AR methods

In this study, Doppler signals recorded from the output of carotid artery of 30 patients were transferred to a personal computer (PC) by using a 16-bit sound card. Doppler difference frequencies were recorded from each of the patients, and then analyzed using fast Fourier transform (FFT) and least squares autoregressive (AR) methods to obtain their sonograms. These sonograms are then used to compare with the applied methods in terms of medical evaluation.     

Non-constrained Blood Pressure Monitoring Using ECG and PPG for Personal Healthcare

Blood pressure (BP) is one of the important vital signs that need to be monitored for personal healthcare. Arterial blood pressure (BP) was estimated from pulse transit time (PTT) and PPG waveform. PTT is a time interval between an R-wave of electrocardiography (ECG) and a photoplethysmography (PPG) signal. This method does not require an aircuff and only a minimal inconvenience of attaching electrodes and LED/photo detector sensors on a subject. PTT computed between the ECG R-wave and the maximum first derivative PPG was strongly correlated with systolic blood pressure (SBP) (R = −0.712) compared with other PTT values, and the diastolic time proved to be appropriate for estimation diastolic blood pressure (DBP) (R = −0.764). The percent errors of SBP using the individual regression line (4–11%) were lower than those using the regression line obtained from all five subjects (9–14%). On the other hand, the DBP estimation did not show much difference between the individual regression (4–10%) and total regression line (6–10%). Our developed device had a total size of 7 × 13.5 cm and was operated by single 3-V battery. Biosignals can be measured for 72 h continuously without external interruptions. Through a serial network communication, an external personal computer can monitor measured waveforms in real time. Our proposed method can be used for non-constrained, thus continuous BP monitoring for the purpose of personal healthcare.     

Inhibitory Effect of Matrine on the Expression of PSA and AR in Prostate Cancer Cell line LNCaP

In order to investigate the inhibitory effect of matrine on the expression of prostate specific antigen （PSA） and androgen receptor （AR） in prostate cancer cell line LNCaP in vitro, LNCaP cells were treated with matrine at different concentrations （0.5, 1.0, 1.5, 2.0 g/L） for 12-36 h. The growth activities of cancer cells were determined by MTT colorimetric assay. The AR level was measured by Western blotting. The expression of PSA was detected by using AXSYM system-chemical luciferase methods. The results showed that matrine could effectively inhibit the growth of androgen-dependent prostate cancer cell line LNCaP in vitro in a time-and dose-dependent manner （P〈0.05）. It could obviously decrease the level of AR （P〈0.01） and inhibit the expression of PSA in a dose-dependent manner （P〈0.05） in LNCaP cells. It was concluded that matrine could significantly suppress the growth of LNCaP cells and inhibit the expression of PSA and AR of prostate cancer cells.     

Acquisition technology research of EEG and related physiological signals under +Gz acceleration

Background

With the continuous improvement of maneuvering performance of modern high-performance aircraft, the protection problem of flight personnel under high G acceleration, the development as well as research on monitoring system and the equipment for human physiological signals processing which include electroencephalogram (EEG) have become more and more important. Due to the particularity of +Gz experimental conditions, the high-risk of human experiments and the great difficulty of dynamic measurement, there is little research on the synchronous acquisition technology of EEG and related physiological signals under +Gz acceleration environment.

Methods

We propose a framework to execute human experiments using the three-axial high-performance human centrifuge, develop reasonable operation mode and design a new experimental research method for EEG signal acquisition and variation characteristics on three-axial high-performance human centrifuge under the environment of +Gz acceleration. We also propose to build the synchronous real-time acquisition plan of EEG, electrocardiogram, brain blood pressure, ear pulse and related physiological signals under centrifuge +Gz acceleration with different equipments and methods.

Results

The good profiles of EEG, heart rate, brain blood pressure and ear pulse are obtained and analyzed comparatively. In addition, the FMS hop-by-hop continuous blood pressure and hemodynamic measurement system Portapres are successfully applied to the ambulatory blood pressure measure under centrifuge +Gz acceleration environment.

Conclusions

The proposed methods establish the basis and have an important guiding significance for follow-up experiment development, EEG features spectral analysis and correlation research of all signals.     

French Claims Data as a Source of Information to Describe Cancer Incidence: Predictive Values of Two Identification Methods of Incident Prostate Cancers

Claims data from the “Programme de Médicalisation du Système d’Information” (PMSI) have been commonly used for several years to complement cancer registries and describe cancer incidence in France. It is less clear whether or not it is possible to use these data as an independent source of information to assess cancer incidence, in the absence of a regional cancer registry. Following a similar study on breast cancer, we present a study which aimed to evaluate two methods of identifying incident prostate cancer using claims data. These methods were developed using claims data from the Hospices Civils de Lyon (HCL) and their validity was tested against medical records. The first method (M1) identified incident patients as those who had at least one stay with a principal diagnosis of prostate cancer. The second method (M2) had a prostate cancer treatment code in addition to the criteria for the first method. Both methods of identification had similar results, indicating a low rate of false negatives (negative predictive values: M1=100 [CI95: 93.8–100], M2=98.6 [CI95: 90.1–99.6]) and a high rate of false positives (positive predictive values: M1=33.3 [CI95: 23.2–42.1], M2=33.7 [CI95: 24.2–43.2]). The sample size did not allow us to produce consistent estimates of sensitivity and specificity. Our results showed that an estimation of the number of incident cases of prostate cancer using both methods of identification would be biased because of the high rate of false positives. Statistical methods that correct identification errors should be used.