Abdulnasir Hossen

Subband decomposition soft-decision algorithm for heart rate variability analysis in patients with obstructive sleep apnea and normal controls

A new method for screening of obstructive sleep apnea (OSA) is investigated. This method is based on the estimation of the energy distribution of the R-R interval (RRI) signals in the time domain. The novelty of the technique arises from the implementation of the soft-decision algorithm of subband decomposition. This soft-decision algorithm will help in finding the ratio of energy (power spectral density (PSD)) in the different frequency bands of the RRI spectrum without implementing any transform technique. Two different ratios--low-frequency/very low-frequency (LF/VLF) and low-frequency/high-frequency (LF/HF)--are used for screening normal and apnea cases. The algorithm can be implemented directly on the (RRI) raw-data or after some pre-processing and filtering steps. The training data used in this study are drawn from the MIT-trial database, while the test data are drawn from the MIT-challenge (chal) database as well as from the sleep disorders laboratory of Sultan Qaboos University (SQU) hospital. Threshold values to identify normal and OSA cases are selected using the receiver operating characteristics (ROC) on the training data. These threshold values are then used for the screening of the test data. The best classification accuracy obtained with the test data (MIT-chal and SQU data) approaches 93% using the LF/VLF ratio. In this case, the sensitivities obtained with MIT-chal and SQU data are 95% and 100%, respectively, while the specificities are 90% and 86% for the same two groups of data.

A new diagnostic test to distinguish tremulous Parkinson's disease from advanced essential tremor

Clinical distinction between advanced essential tremor and tremulous Parkinsons disease can be difficult.

A wavelet-based soft decision technique for screening of patients with congestive heart failure

Abstract A wavelet-decomposition with soft decision algorithm is used to estimate an approximate power spectral density (PSD) of R–R intervals (RRI) of ECG data for the purpose of screening of congestive heart failure (CHF) from normal subjects. The ratio of the power in the low-frequency (LF) band to the power in the high-frequency (HF) band of the RRI signal is used as the classification factor. The trial data used for estimating of the classification factor consist of 15 CHF (patient) subjects and 12 normal sinus rhythm (NSR) or simply normal subjects. The performance of the algorithm is then evaluated on test data set, which consists of 17 CHF subjects and 53 NSR subjects. Both trial and test data are drawn from MIT database. The receiver operating characteristics (ROC) is used to determine the threshold value of the classification factor. Results are shown for different wavelets filters. The new technique shows a classification efficiency of 96.30% on trial data and 88.57% on test data. An FFT-based frequency domain screening technique is also implemented and included in this work for the purpose of comparison with the wavelet-based technique. The FFT-based technique shows an efficiency of classification of 99.63% on trial data and 81.42% on test data. The comparison is also done on short-term (5-min) recordings. The wavelet-based soft-decision technique shows also better results than the FFT-based technique.

Classification of modulation signals using statistical signal characterization and artificial neural networks

Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification.

Identification of patients with congestive heart failure using different neural networks approaches

A new technique for identification of patients with congestive heart failure (CHF) from normal controls is investigated in this paper using spectral analysis and neural networks. The identification system consists of two parts: feature extraction part and classification part. The feature extraction part uses the method of approximate spectral density estimation of R-R-Intervals (RRI) data by implementing the soft decision sub-band decomposition technique. In the classification part, two different methods of machine learning approaches with neural networks are implemented and compared in their performances. Those approaches are: supervised neural network (back-propagation) and unsupervised neural network (Kohonen self organizing maps). The data used in this work is obtained from Massachusetts Institute of Technology (MIT) databases. A data set of 17 CHF and 53 normal subjects is used as original training data set, while another set of 12 CHF and 12 normal subjects is used as original test data set. The classification features are the spectral density of 6 different regions covering the whole spectrum of the RRI data obtained by 32-bands soft decision algorithm. A larger training data set, which is obtained by simulating 1000 CHF and 1000 normal subjects according to the spectral features obtained from the original training data, is used to train the neural network. The neural network is used then to test another simulated data set of the same size of the training date set (simulated according to the spectral features obtained from the original test data set). The accuracy of the classification is found to be about 83.65% and 91.43% with supervised neural networks and unsupervised neural networks respectively.

The importance of the very low frequency power of heart rate variability in screening of patients with obstructive sleep Apnea

Sleep apnea is a complete or partial cessation of breathing during sleep. Obstructive sleep Apnea (OSA) is the common form of apnea that occurs when the upper airway is partially or completely obstructed due to the relaxation of dilating muscles. In developed countries the cost of investigating patients has increased considerably during the last decade as the only reliable method for the diagnosis of OSA until now is overnight sleep studies (Polysomnography), which is a cumbersome, time consuming and expensive procedure requiring specially trained polysomnographers and needs recording of ECG, EEG, EMG, EOG, nasal air respiratory effort and oxygen saturation.

A neural network approach for feature extraction and discrimination between Parkinsonian tremor and essential tremor

BACKGROUND Essential tremor (ET) and the tremor in Parkinsons disease (PD) are the two most common pathological tremor with a certain overlap in the clinical presentation. OBJECTIVE The main purpose of this work is to use an artificial neural network to select the best features and to discriminate between the two types of tremors using spectral analysis of tremor time-series recorded by accelerometry and surface EMG signals. METHODS The Soft-Decision wavelet-based technique is to be used in this work in order to obtain a 16 bands approximate spectral representation of both accelerometer and two EMG signals of two sets of data (training and test). The training set consists of 21 ET subjects and 19 PD subjects while the test set consists of 20 ET and 20 PD subjects. The data has been recorded for diagnostic purposes in the Department of Neurology of the University of Kiel, Germany. A neural network of the type feed forward back propagation has been used to find the frequency bands associated with the different signals that yield better discrimination efficiency on training data. The same designed network is used to discriminate the test set. RESULTS Efficiency result of 87.5% was obtained using two different bands from each of the three signals under test. CONCLUSIONS The artificial neural network has been used successfully in both feature extraction and in pattern matching tasks in a complete classification system.

Classification of sleep apnea using wavelet-based spectral analysis of heart rate variability

BACKGROUND Obstructive Sleep Apnea (OSA) is the cessation of breathing during sleep due to the collapse of upper airway. Polysomnographic recording is a conventional method for detection of OSA. Although it provides reliable results, it is expensive and cumbersome. Thus, an advanced non-invasive signal processing based technique is needed. OBJECTIVE The main purpose of this work is to predict the severity of sleep apnea using an efficient wavelet-based spectral analysis method of the heart rate variability (HRV) to classify sleep apnea into three different levels (mild, moderate, and severe) according to its severity and to distinguish them from normal subjects. METHODS The standard FFT spectrum analysis method and the soft-decision wavelet-based technique are to be used in this work in order to rank patients to full polysomnography. Data of 20 normal subjects and 20 patients with mild apnea and 20 patients with moderate apnea and 20 patients of severe apnea are used in this study. The data is obtained from the sleep laboratory of Sultan Qaboos University hospital in Oman. Four different classification versions have been used in this work. RESULTS Accuracy result of 90% was obtained between severe and normal subjects and 85% between mild and normal and 75% between severe and moderate and 83.75% between normal and patients. CONCLUSIONS The VLF/LF power spectral ratio of the wavelet-based soft-decision analysis of the RRI data after a high-pass filter resulted in the best accuracy of classification in all versions.

Identification of patients with preeclampsia from normal subjects using wavelet-based spectral analysis of heart rate variability

BACKGROUND The spectral analysis of the heart rate variability (HRV) shows a decrease in the power of the high frequency (HF) component in preeclamptic pregnancy compared with normal pregnancy; such a decrease is associated with an increase in the low frequency (LF) and the very low frequency (VLF) power. The physiological interpretation is that preeclamptic pregnancy is associated with a facilitation of sympathetic regulation and an attenuation of parasympathetic influence of HR compared with non-pregnancy and normal pregnancy. OBJECTIVE To use an efficient nased on spectral analysis non-invasive technique to identify preeclamptic pregnant subjects from normal pregnant in Oman. METHODS The soft-decision wavelet-based technique is implemented to find the power of the HRV bands in high resolution manner compared to the classical fast Fourier Transform method. Data was obtained from 20 preeclamptic pregnant subjects and 20 normal pregnant controls of the same pregnancy duration, obtained from Nizwa and Sultan Qaboos University hospitals in Oman. RESULTS The soft-decision wavelet method succeeds to identify patients from normal pregnant with specificity, sensitivity and accuracy of 90%, 80% and 85%, respectively, compared to the FFT which results in 75% specificity, sensitivity and accuracy. CONCLUSION The LF power obtained by Soft-decision wavelet decomposition is shown to be a successful feature for identification of preeclampsia.

Investigation of heart rate variability of patients undergoing coronary artery bypass grafting (CABG)

BACKGROUND Myocardial revascularization by coronary artery bypass grafting (CABG) is an effective measure for reducing symptoms and mortality in patients with unstable or severe coronary artery disease (CAD). Autonomic function can be estimated non-invasively using heart rate variability (HRV). HRV of patients undergoing CABG is investigated before and after CABG using a soft-decision wavelet based spectral analysis. OBJECTIVE The main purpose of this work is to evaluate non-invasively HRV in patients undergoing CABG before operation; and to monitor the status of patients through HRV investigation on day 6 and day 30 after the CABG operation. The study intends to contribute scientific value to understanding the effect of CABG on the cardiovascular autonomic function and surgical outcome. METHODS The soft-decision wavelet-based technique is used in this work in order to measure the power spectral density of the three main bands (VLF, LF, and HF) of HRV in 24 patients undergoing CABG operation, before the operation (Group 1: G1), and 6 days after operation (Group 2: G2) and 30 days after operation (Group 3: G3). The data is obtained from Sultan Qaboos University hospital in Oman. RESULTS The HF power increases in 22 out of 24 patients in G2 compared to G1. While the LF power decreases in 21 out of 24 patients in G2 compared to G1. Comparing G3 to G1 the LF power decreases in 20 patients. The sum of the VLF and LF power is reduced in G2 in all 24 subjects compared to G1, and in 19 subjects in G3 compared to G1. CONCLUSIONS The power spectral density of the HF shows increase in patients recorded on day 6 after operation compared to patients before the operation. The LF shows a decrease in G2 compared to G1. The results of G3 after 30 days of operation still show an increase of the HF power and a decrease in the LF power in most of the patients compared to their values before operation.