Computer-aided classification of small airways dysfunction using impulse oscillometric features: a children-focused review.

Background and objective Spirometry, which is the most commonly used technique for asthma diagnosis, is often unsuitable for small children as it requires them to follow exact instructions and perform extreme inspiration and expiration maneuvers. In contrast, impulse oscillometry (IOS) is a child-friendly technique that could serve as an alternative pulmonary function test (PFT) for asthma diagnosis and control in children as it offers several advantages over spirometry. However, the complex test results of IOS may be difficult to be understood by practitioners due to its reliance on mechanical and electrical models of the human pulmonary system. Recognizing this reality, computer-aided decision systems could help to improve the utility of IOS. The main objective of this paper is to understand the current computer-aided classification research works on this topic. Methods This paper presents a methodological review of research works related to the computer-aided classification of peripheral airway obstruction using the IOS technique, which is focused on, but not limited to, asthmatic children. Publications that focused on computer-aided classification of asthma, peripheral dysfunction and/or small airway impairment (SAI) based on impulse oscillometric features were selected for this review. Results Out of the 34 articles that were identified using the selected scientific web databases and topic-related parameters, only eight met the eligibility criteria. The most relevant results of the articles reviewed are related to the performance of the different classifiers using static features which are solely based on the first pulmonary function testing measurements (IOS and spirometry). These results included an overall classifiers' accuracy performance ranging from 42.24% to 98.61%. Conclusion There is still a great opportunity to improve the utility of IOS by developing more computer-aided robust classifiers, specifically for the asthmatic children population as the classification studies performed to date (1) are limited in number, (2) include features derived from tests that are not optimally suitable for children, (3) are solely bi-class (mostly asthma and non-asthma) and therefore fail to include different degrees of peripheral obstruction for disease prevention and control and (4) lack of validation in cases that focus on multi-class classification of the different degrees of peripheral airway obstruction.

The Conceptual Design of a Novel Workstation for Seizure Prediction Using Machine Learning With Potential eHealth Applications.

Recent attempts to predict refractory epileptic seizures using machine learning algorithms to process electroencephalograms (EEGs) have shown great promise. However, research in this area requires a specialized workstation. Commercial solutions are unsustainably expensive, can be unavailable in most countries, and are not designed specifically for seizure prediction research. On the other hand, building the optimal workstation is a complex task, and system instability can arise from the least obvious sources imaginable. Therefore, the absence of a template for a dedicated seizure prediction workstation in today's literature is a formidable obstacle to seizure prediction research. To increase the number of researchers working on this problem, a template for a dedicated seizure prediction workstation needs to become available. This paper proposes a novel dedicated system capable of machine learning-based seizure prediction and training for under U.S. $1000, which is significantly less expensive (U.S. $700 or more) than comparable commercial solutions. This powerful workstation will be capable of training sophisticated machine learning algorithms that can be deployed to lightweight wearable devices, which enables the creation of wearable EEG-based seizure early warning systems.

Vital Sign Monitoring and Cardiac Triggering at 1.5 Tesla: A Practical Solution by an MR-Ballistocardiography Fiber-Optic Sensor.

This article presents a solution for continuous monitoring of both respiratory rate (RR) and heart rate (HR) inside Magnetic Resonance Imaging (MRI) environments by a novel ballistocardiography (BCG) fiber-optic sensor. We designed and created a sensor based on the Fiber Bragg Grating (FBG) probe encapsulated inside fiberglass (fiberglass is a composite material made up of glass fiber, fabric, and cured synthetic resin). Due to this, the encapsulation sensor is characterized by very small dimensions (30 × 10 × 0.8 mm) and low weight (2 g). We present original results of real MRI measurements (conventionally most used 1.5 T MR scanner) involving ten volunteers (six men and four women) by performing conventional electrocardiography (ECG) to measure the HR and using a Pneumatic Respiratory Transducer (PRT) for RR monitoring. The acquired sensor data were compared against real measurements using the objective Bland⁻Altman method, and the functionality of the sensor was validated (95.36% of the sensed values were within the ±1.96 SD range for the RR determination and 95.13% of the values were within the ±1.96 SD range for the HR determination) by this means. The accuracy of this sensor was further characterized by a relative error below 5% (4.64% for RR and 4.87% for HR measurements). The tests carried out in an MRI environment demonstrated that the presence of the FBG sensor in the MRI scanner does not affect the quality of this imaging modality. The results also confirmed the possibility of using the sensor for cardiac triggering at 1.5 T (for synchronization and gating of cardiovascular magnetic resonance) and for cardiac triggering when a Diffusion Weighted Imaging (DWI) is used.

Comparative Effectiveness of ICA and PCA in Extraction of Fetal ECG From Abdominal Signals: Toward Non-invasive Fetal Monitoring.

Non-adaptive signal processing methods have been successfully applied to extract fetal electrocardiograms (fECGs) from maternal abdominal electrocardiograms (aECGs); and initial tests to evaluate the efficacy of these methods have been carried out by using synthetic data. Nevertheless, performance evaluation of such methods using real data is a much more challenging task and has neither been fully undertaken nor reported in the literature. Therefore, in this investigation, we aimed to compare the effectiveness of two popular non-adaptive methods (the ICA and PCA) to explore the non-invasive (NI) extraction (separation) of fECGs, also known as NI-fECGs from aECGs. The performance of these well-known methods was enhanced by an adaptive algorithm, compensating amplitude difference and time shift between the estimated components. We used real signals compiled in 12 recordings (real01-real12). Five of the recordings were from the publicly available database (PhysioNet-Abdominal and Direct Fetal Electrocardiogram Database), which included data recorded by multiple abdominal electrodes. Seven more recordings were acquired by measurements performed at the Institute of Medical Technology and Equipment, Zabrze, Poland. Therefore, in total we used 60 min of data (i.e., around 88,000 R waves) for our experiments. This dataset covers different gestational ages, fetal positions, fetal positions, maternal body mass indices (BMI), etc. Such a unique heterogeneous dataset of sufficient length combining continuous Fetal Scalp Electrode (FSE) acquired and abdominal ECG recordings allows for robust testing of the applied ICA and PCA methods. The performance of these signal separation methods was then comprehensively evaluated by comparing the fetal Heart Rate (fHR) values determined from the extracted fECGs with those calculated from the fECG signals recorded directly by means of a reference FSE. Additionally, we tested the possibility of non-invasive ST analysis (NI-STAN) by determining the T/QRS ratio. Our results demonstrated that even though these advanced signal processing methods are suitable for the non-invasive estimation and monitoring of the fHR information from maternal aECG signals, their utility for further morphological analysis of the extracted fECG signals remains questionable and warrants further work.

A review on wearable photoplethysmography sensors and their potential future applications in health care.

Photoplethysmography (PPG) is an uncomplicated and inexpensive optical measurement method that is often used for heart rate monitoring purposes. PPG is a non-invasive technology that uses a light source and a photodetector at the surface of skin to measure the volumetric variations of blood circulation. Recently, there has been much interest from numerous researchers around the globe to extract further valuable information from the PPG signal in addition to heart rate estimation and pulse oxymetry readings. PPG signal's second derivative wave contains important health-related information. Thus, analysis of this waveform can help researchers and clinicians to evaluate various cardiovascular-related diseases such as atherosclerosis and arterial stiffness. Moreover, investigating the second derivative wave of PPG signal can also assist in early detection and diagnosis of various cardiovascular illnesses that may possibly appear later in life. For early recognition and analysis of such illnesses, continuous and real-time monitoring is an important approach that has been enabled by the latest technological advances in sensor technology and wireless communications. The aim of this article is to briefly consider some of the current developments and challenges of wearable PPG-based monitoring technologies and then to discuss some of the potential applications of this technology in clinical settings.

Non-Invasive Fetal Monitoring: A Maternal Surface ECG Electrode Placement-Based Novel Approach for Optimization of Adaptive Filter Control Parameters Using the LMS and RLS Algorithms.

This paper is focused on the design, implementation and verification of a novel method for the optimization of the control parameters (such as step size µ and filter order N) of LMS and RLS adaptive filters used for noninvasive fetal monitoring. The optimization algorithm is driven by considering the ECG electrode positions on the maternal body surface in improving the performance of these adaptive filters. The main criterion for optimal parameter selection was the Signal-to-Noise Ratio (SNR). We conducted experiments using signals supplied by the latest version of our LabVIEW-Based Multi-Channel Non-Invasive Abdominal Maternal-Fetal Electrocardiogram Signal Generator, which provides the flexibility and capability of modeling the principal distribution of maternal/fetal ECGs in the human body. Our novel algorithm enabled us to find the optimal settings of the adaptive filters based on maternal surface ECG electrode placements. The experimental results further confirmed the theoretical assumption that the optimal settings of these adaptive filters are dependent on the ECG electrode positions on the maternal body, and therefore, we were able to achieve far better results than without the use of optimization. These improvements in turn could lead to a more accurate detection of fetal hypoxia. Consequently, our approach could offer the potential to be used in clinical practice to establish recommendations for standard electrode placement and find the optimal adaptive filter settings for extracting high quality fetal ECG signals for further processing. Ultimately, diagnostic-grade fetal ECG signals would ensure the reliable detection of fetal hypoxia.

A Phonocardiographic-Based Fiber-Optic Sensor and Adaptive Filtering System for Noninvasive Continuous Fetal Heart Rate Monitoring.

This paper focuses on the design, realization, and verification of a novel phonocardiographic- based fiber-optic sensor and adaptive signal processing system for noninvasive continuous fetal heart rate (fHR) monitoring. Our proposed system utilizes two Mach-Zehnder interferometeric sensors. Based on the analysis of real measurement data, we developed a simplified dynamic model for the generation and distribution of heart sounds throughout the human body. Building on this signal model, we then designed, implemented, and verified our adaptive signal processing system by implementing two stochastic gradient-based algorithms: the Least Mean Square Algorithm (LMS), and the Normalized Least Mean Square (NLMS) Algorithm. With this system we were able to extract the fHR information from high quality fetal phonocardiograms (fPCGs), filtered from abdominal maternal phonocardiograms (mPCGs) by performing fPCG signal peak detection. Common signal processing methods such as linear filtering, signal subtraction, and others could not be used for this purpose as fPCG and mPCG signals share overlapping frequency spectra. The performance of the adaptive system was evaluated by using both qualitative (gynecological studies) and quantitative measures such as: Signal-to-Noise Ratio-SNR, Root Mean Square Error-RMSE, Sensitivity-S+, and Positive Predictive Value-PPV.

A Non-Invasive Multichannel Hybrid Fiber-Optic Sensor System for Vital Sign Monitoring.

In this article, we briefly describe the design, construction, and functional verification of a hybrid multichannel fiber-optic sensor system for basic vital sign monitoring. This sensor uses a novel non-invasive measurement probe based on the fiber Bragg grating (FBG). The probe is composed of two FBGs encapsulated inside a polydimethylsiloxane polymer (PDMS). The PDMS is non-reactive to human skin and resistant to electromagnetic waves, UV absorption, and radiation. We emphasize the construction of the probe to be specifically used for basic vital sign monitoring such as body temperature, respiratory rate and heart rate. The proposed sensor system can continuously process incoming signals from up to 128 individuals. We first present the overall design of this novel multichannel sensor and then elaborate on how it has the potential to simplify vital sign monitoring and consequently improve the comfort level of patients in long-term health care facilities, hospitals and clinics. The reference ECG signal was acquired with the use of standard gel electrodes fixed to the monitored person's chest using a real-time monitoring system for ECG signals with virtual instrumentation. The outcomes of these experiments have unambiguously proved the functionality of the sensor system and will be used to inform our future research in this fast developing and emerging field.

BUILDing SCHOLARS: enhancing diversity among U.S. biomedical researchers in the Southwest.

BACKGROUND AND PURPOSE: With funding from the National Institutes of Health, BUILDing SCHOLARS was established at The University of Texas at El Paso with the goal of implementing, evaluating and sustaining a suite of institutional, faculty and student development interventions in order to train the next generation of biomedical researchers from the U.S. Southwest region, where the need is dire among underserved communities. The focus is on supporting the infrastructure necessary to train and mentor students so they persist on pathways across a range of biomedical research fields. The purpose of this article is to highlight the design and implementation of BUILDing SCHOLARS' key interventions, which offer a systemic student training model for the U.S. Southwest. In-depth reporting of evaluation results is reserved for other technical publications. PROGRAM AND KEY HIGHLIGHTS: BUILDing SCHOLARS uses a comprehensive regional approach to undergraduate training through a multi-institution consortium that includes 12 research partners and various pipeline partners across Texas, New Mexico, and Arizona. Through faculty collaborations and undergraduate research training, the program integrates social and behavioral sciences and biomedical engineering while emphasizing seven transdisciplinary nodes of biomedical research excellence that are common across partner institutions: addiction, cancer, degenerative and chronic diseases, environmental health, health disparities, infectious diseases, and translational biomedicine. Key interventions aim to: (1) improve institutional capacities by expanding undergraduate research training infrastructures; (2) develop an intra- and cross-institutional mentoring-driven "community of practice" to support undergraduate student researchers; (3) broaden the pool of student participants, improve retention, and increase matriculation into competitive graduate programs; and (4) support faculty and postdoctoral personnel by training them in research pedagogy and mentoring techniques and providing them with resources for increasing their research productivity. Student training activities focus on early interventions to maximize retention and on enabling students to overcome common barriers by addressing their educational endowments, science socialization, network development, family expectations, and material resources. Over the long term, BUILDing SCHOLARS will help increase the diversity of the biomedical research workforce in the U.S. by meeting the needs of students from the Southwest region and by serving as a model for other institutions.

A novel LabVIEW-based multi-channel non-invasive abdominal maternal-fetal electrocardiogram signal generator.

This paper describes the design, construction, and testing of a multi-channel fetal electrocardiogram (fECG) signal generator based on LabVIEW. Special attention is paid to the fetal heart development in relation to the fetus' anatomy, physiology, and pathology. The non-invasive signal generator enables many parameters to be set, including fetal heart rate (FHR), maternal heart rate (MHR), gestational age (GA), fECG interferences (biological and technical artifacts), as well as other fECG signal characteristics. Furthermore, based on the change in the FHR and in the T wave-to-QRS complex ratio (T/QRS), the generator enables manifestations of hypoxic states (hypoxemia, hypoxia, and asphyxia) to be monitored while complying with clinical recommendations for classifications in cardiotocography (CTG) and fECG ST segment analysis (STAN). The generator can also produce synthetic signals with defined properties for 6 input leads (4 abdominal and 2 thoracic). Such signals are well suited to the testing of new and existing methods of fECG processing and are effective in suppressing maternal ECG while non-invasively monitoring abdominal fECG. They may also contribute to the development of a new diagnostic method, which may be referred to as non-invasive trans-abdominal CTG + STAN. The functional prototype is based on virtual instrumentation using the LabVIEW developmental environment and its associated data acquisition measurement cards (DAQmx). The generator also makes it possible to create synthetic signals and measure actual fetal and maternal ECGs by means of bioelectrodes.

Exploring the Nature of the Intention, Meaning and Perception Process of the Neuro-occupation Model to Understand Adaptation to Change.

The theoretical model of neuro-occupation, intention, meaning and perception, sought to describe the symbiotic relationship between occupation and the brain, as a chaotic, self-organized, complex system. Lack of evidence has limited its applicability to practice. The aim of this study was to track the postulates of the model within the daily experiences of subjects. Structured matrices were created for content analysis, using a qualitative multiple-case-study design, typically used for testing models. An underpinning principle of the model, defined a circular causality feedback process, which was confirmed as described through tracing the repetitive processes within the lived experience of two Iranian men. The process suggested that continual adaptation occurred in lives interrupted by cerebrovascular accident, which enabled the subjects to return to expression of meaning through purposeful occupation and continually re-shaped their perceptions. The primary limitation of this study was that it was the earliest attempt to test the model and to substantiate the process by comparing the similarities and differences between too few subjects. Future research should identify the same process in more subjects and validate a practical assessment tool for clients. These findings may inform practitioners about intentional use of occupational challenges to elicit adaptive behaviours in clients.

Automatic sleep staging using empirical mode decomposition, discrete wavelet transform, time-domain, and nonlinear dynamics features of heart rate variability signals.

The conventional method for sleep staging is to analyze polysomnograms (PSGs) recorded in a sleep lab. The electroencephalogram (EEG) is one of the most important signals in PSGs but recording and analysis of this signal presents a number of technical challenges, especially at home. Instead, electrocardiograms (ECGs) are much easier to record and may offer an attractive alternative for home sleep monitoring. The heart rate variability (HRV) signal proves suitable for automatic sleep staging. Thirty PSGs from the Sleep Heart Health Study (SHHS) database were used. Three feature sets were extracted from 5- and 0.5-min HRV segments: time-domain features, nonlinear-dynamics features and time-frequency features. The latter was achieved by using empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods. Normalized energies in important frequency bands of HRV signals were computed using time-frequency methods. ANOVA and t-test were used for statistical evaluations. Automatic sleep staging was based on HRV signal features. The ANOVA followed by a post hoc Bonferroni was used for individual feature assessment. Most features were beneficial for sleep staging. A t-test was used to compare the means of extracted features in 5- and 0.5-min HRV segments. The results showed that the extracted features means were statistically similar for a small number of features. A separability measure showed that time-frequency features, especially EMD features, had larger separation than others. There was not a sizable difference in separability of linear features between 5- and 0.5-min HRV segments but separability of nonlinear features, especially EMD features, decreased in 0.5-min HRV segments. HRV signal features were classified by linear discriminant (LD) and quadratic discriminant (QD) methods. Classification results based on features from 5-min segments surpassed those obtained from 0.5-min segments. The best result was obtained from features using 5-min HRV segments classified by the LD classifier. A combination of linear/nonlinear features from HRV signals is effective in automatic sleep staging. Moreover, time-frequency features are more informative than others. In addition, a separability measure and classification results showed that HRV signal features, especially nonlinear features, extracted from 5-min segments are more discriminative than those from 0.5-min segments in automatic sleep staging.

Wireless photoplethysmographic device for heart rate variability signal acquisition and analysis.

The photoplethysmographic (PPG) signal has the potential to aid in the acquisition and analysis of heart rate variability (HRV) signal: a non-invasive quantitative marker of the autonomic nervous system that could be used to assess cardiac health and other physiologic conditions. A low-power wireless PPG device was custom-developed to monitor, acquire and analyze the arterial pulse in the finger. The system consisted of an optical sensor to detect arterial pulse as variations in reflected light intensity, signal conditioning circuitry to process the reflected light signal, a microcontroller to control PPG signal acquisition, digitization and wireless transmission, a receiver to collect the transmitted digital data and convert them back to their analog representations. A personal computer was used to further process the captured PPG signals and display them. A MATLAB program was then developed to capture the PPG data, detect the RR peaks, perform spectral analysis of the PPG data, and extract the HRV signal. A user-friendly graphical user interface (GUI) was developed in LabView to display the PPG data and their spectra. The performance of each module (sensing unit, signal conditioning, wireless transmission/reception units, and graphical user interface) was assessed individually and the device was then tested as a whole. Consequently, PPG data were obtained from five healthy individuals to test the utility of the wireless system. The device was able to reliably acquire the PPG signals from the volunteers. To validate the accuracy of the MATLAB codes, RR peak information from each subject was fed into Kubios software as a text file. Kubios was able to generate a report sheet with the time domain and frequency domain parameters of the acquired data. These features were then compared against those calculated by MATLAB. The preliminary results demonstrate that the prototype wireless device could be used to perform HRV signal acquisition and analysis.

Analysis of impulse oscillometric measures of lung function and respiratory system model parameters in small airway-impaired and healthy children over a 2-year period.

BACKGROUND: Is Impulse Oscillometry System (IOS) a valuable tool to measure respiratory system function in Children? Asthma (A) is the most prevalent chronic respiratory disease in children. Therefore, early and accurate assessment of respiratory function is of tremendous clinical interest in diagnosis, monitoring and treatment of respiratory conditions in this subpopulation. IOS has been successfully used to measure lung function in children with a high degree of sensitivity and specificity to small airway impairments (SAI) and asthma. IOS measures of airway function and equivalent electrical circuit models of the human respiratory system have been developed to quantify the severity of these conditions. Previously, we have evaluated several known respiratory models based on the Mead's model and more parsimonious versions based on fitting IOS data known as extended RIC (eRIC) and augmented RIC (aRIC) models have emerged, which offer advantages over earlier models. METHODS: IOS data from twenty-six children were collected and compared during pre-bronchodilation (pre-B) and post- bronchodilation (post-B) conditions over a period of 2 years. RESULTS AND DISCUSSION: Are the IOS and model parameters capable of differentiating between healthy children and children with respiratory system distress? Children were classified into two main categories: Healthy (H) and Small Airway-Impaired (SAI). The IOS measures and respiratory model parameters analyzed differed consistently between H and SAI children. SAI children showed smaller trend of "growth" and larger trend of bronchodilator responses than H children.The two model parameters: peripheral compliance (Cp) and peripheral resistance (Rp) tracked IOS indices of small airway function well. Cp was a more sensitive index than Rp. Both eRIC and aRIC Cps and the IOS Reactance Area, AX, (also known as the "Goldman Triangle") showed good correlations. CONCLUSIONS: What are the most useful IOS and model parameters? In this work we demonstrate that IOS parameters such as resistance at 5 Hz (R5), frequency-dependence of resistance (fdR: R5-R20), reactance area (AX), and parameter estimates of respiratory system such as Cp and Rp provide sensitive indicators of lung function and have the capacity to differentiate between obstructed and non-obstructed airway conditions. They are also capable of demonstrating airway growth-related changes over a two-year period. We conclude that the IOS parameters AX and the eRIC model derived parameter Cp are the most reliable parameters to track lung function in children before and after bronchodilator and over a time period (2 years). Which model is more suitable for interpreting IOS data? IOS data are equally well-modelled by eRIC and aRIC models, based on the close correlations of their corresponding parameters - excluding upper airway shunt compliance. The eRIC model is a more parsimonious and equally powerful model in capturing the differences in IOS indices between SAI and H children. Therefore, it may be considered a clinically-preferred model of lung function.

Circuit analysis justifies a reduced Mead's model of the human respiratory impedance for impulse oscillometry data.

Recent attempts at estimating the parameters for respiratory impedance models from data obtained by Impulse Oscillometry (IOS) have come across difficulties when using the well-established Mead's model of human respiratory impedance. Unconstrained optimization of this model often yields values of chest wall compliance (C(W)) and lung compliance (C(l)) too large to be physiologically feasible. We hypothesize that IOS volume displacements are inconsequential to the lung tissue and chest wall due to the small contributions of these displacements relative to lung capacity. In order to explore the validity of this hypothesis we performed a detailed analysis of Mead's impedance model. The IOS input flow signal was approximated by using a combination of typical waveforms, this signal was then used to excite Mead's electrical circuit model of the respiratory impedance with physiologically realistic parameter values estimated using data obtained from one normal adult, ten adult patients with Cystic Fibrosis, ten patients with Asthma and ten normal children, with focus on normal adult data. Pressure waveforms, energy and integrated pressure values were then obtained and compared at different points of interest in the model. This investigation suggests that the pressures "felt" by the lung tissue and chest wall are too small to have a noticeable effect on them therefore making those particular circuit elements unnecessary when the respiratory system is subject to small displacement volumes such as those used in Impulse Oscillometry. Furthermore, we believe that the very large parameter values often obtained with unconstrained optimization of Mead's model are evidence that C(l) and C(w) could be "shorted-out" when modeling IOS data.

Electrical circuit models of the human respiratory system reflect small airway impairment measured by impulse oscillation (IOS).

The use of the forced oscillatory input impedance parameter, frequency-dependence of Resistance (fdR), to assess small airway impairment (SAI) has not been widely accepted due to concern about the effects of "upper airway shunt" on oscillometric resistance and low frequency reactance. On the other hand, recent medical studies suggest that low frequency reactance is a very sensitive index of treatment intervention directed at small airways. The present study was undertaken to analyze and compare Impulse Oscillometry (IOS) resistance and reactance data with model-derived indices of small airway function from two models of the respiratory impedance, one with, and the other without an element for upper airway shunt capacitance. Fifty six patients with stable chronic obstructive lung disease of varying severity due to Cystic Fibrosis (CF) and 21 patients with asthma were evaluated by IOS testing. IOS data were input into the augmented RIC (aRIC) model with an upper airway shunt capacitance, and the extended RIC (eRIC) model, without a shunt capacitance element. Model-derived indices were compared between the two models for CF patients separately from asthma patients. We conclude that IOS indices of SAI are modeled equally well with or without upper airway shunt capacitance, and do not seem to be dependent on upper airway shunt capacitance.

Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients.

Currently in the world there is an alarming number of people who suffer from sleep disorders. A number of biomedical signals, such as EEG, EMG, ECG and EOG are used in sleep labs among others for diagnosis and treatment of sleep related disorders. The usual method for sleep stage classification is visual inspection by a sleep specialist. This is a very time consuming and laborious exercise. Automatic sleep stage classification can facilitate this process. The definition of sleep stages and the sleep literature show that EEG signals are similar in Stage 1 of non-rapid eye movement (NREM) sleep and rapid eye movement (REM) sleep. Therefore, in this work an attempt was made to classify four sleep stages consisting of Awake, Stage 1 + REM, Stage 2 and Slow Wave Stage based on the EEG signal alone. Wavelet packet coefficients and artificial neural networks were deployed for this purpose. Seven all night recordings from Physionet database were used in the study. The results demonstrated that these four sleep stages could be automatically discriminated from each other with a specificity of 94.4 +/- 4.5%, a of sensitivity 84.2+3.9% and an accuracy of 93.0 +/- 4.0%.

Impulse oscillometric features of lung function: towards computer-aided classification of respiratory diseases in children.

Asthma is the most prevalent chronic respiratory disease in children. Reliable and patient-friendly instruments and methods are required to help pulmonologists accurately detect asthma with acceptable clinical accuracy, specificity and sensitivity. Impulse Oscillometry System (IOS) based on the Forced Oscillation Technique (FOT) has been successfully used to measure lung function in children with a high degree of sensitivity and specificity to small airway dysfunction (SAD). IOS measures the mechanical impedance of the respiratory system. Equivalent electrical circuit models of lung function have been developed that can be used to quantify severity of SAD. It has been shown that impulse oscillometric parameters as well as parameter estimates of these electrical models provide useful indicators of lung function and therefore have the potential to be used as sensitive features for computer-aided classification of pulmonary function in health and disease.

Development of an Intelligent PDA-based Wearable Digital Phonocardiograph.

Last year at the EMBC 2004 in San Francisco, we presented a paper entitled: "Digital Phonocardiography: a PDA-based Approach", which introduced the development of a PDA-based biomedical instrument capable of acquiring, processing, and analysis of heart sounds. In this paper we present a system, which is not only able to record and display the heart sounds in a Pocket PC but also apply several signal processing and statistical techniques to segment the these signals into four parts (the first heart sound, the systole, the second heart sound and the diastole) and implement feature extraction methods for classification purposes. Classification has been achieved using a Multilayer Perceptron (MLP) Artificial Neural Network (ANN). The system was used to classify a number of normal and abnormal heart sounds (normal, aortic regurgitation, aortic stenosis, mitral regurgitation and mitral stenosis) and validate the effectiveness of the statistical segmentation and the feature extraction methods in this environment.

A PDA-based Network for Telemonitoring Asthma Triggering Gases in the El Paso School Districts of the US - Mexico Border Region.

In this paper we describe the application of a personal digital assistant (PDA) or pocket PC as an effective communication device to telemonitor levels of asthma triggering gases collected from a remote location under test to a workstation which has a personal computer (PC) running on Windows XP® as the operating system. The Bluetooth® features of the PDA are explored to transmit data collected by a Direct™ Sense Tox toxic gas monitor equipped with five toxic gas probes and one temperature sensor in real time, thereby making this telemonitoring system an innovative instrument in monitoring levels of asthma triggering gases in the El Paso-border metropolitan region, a region in which asthma is highly prevalent especially in children. At the workstation or fixed location these readings are displayed using a custom made, user friendly graphical user interface (GUI) developed using software tools like action scripting with Macromedia® Flash™. The growing advancement in technology and ever diminishing sizes of handheld devices encouraged us to opt for this configuration. Moreover, the PDA and toxic gas monitor were also chosen for their light weight, portability, flexibility, low cost and data collection and transmission capabilities.