Asela Samantha Karunajeewa

Silence-breathing-snore classification from snore-related sounds.

Obstructive sleep apnea (OSA) is a highly prevalent disease in which upper airways are collapsed during sleep, leading to serious consequences. Snoring is the earliest symptom of OSA, but its potential in clinical diagnosis is not fully recognized yet. The first task in the automatic analysis of snore-related sounds (SRS) is to segment the SRS data as accurately as possible into three main classes: snoring (voiced non-silence), breathing (unvoiced non-silence) and silence. SRS data are generally contaminated with background noise. In this paper, we present classification performance of a new segmentation algorithm based on pattern recognition. We considered four features derived from SRS to classify samples of SRS into three classes. The features--number of zero crossings, energy of the signal, normalized autocorrelation coefficient at 1 ms delay and the first predictor coefficient of linear predictive coding (LPC) analysis--in combination were able to achieve a classification accuracy of 90.74% in classifying a set of test data. We also investigated the performance of the algorithm when three commonly used noise reduction (NR) techniques in speech processing--amplitude spectral subtraction (ASS), power spectral subtraction (PSS) and short time spectral amplitude (STSA) estimation--are used for noise reduction. We found that noise reduction together with a proper choice of features could improve the classification accuracy to 96.78%, making the automated analysis a possibility.

Multi-feature snore sound analysis in obstructive sleep apnea-hypopnea syndrome.

Snoring is the most common symptom of obstructive sleep apnea hypopnea syndrome (OSAHS), which is a serious disease with high community prevalence. The standard method of OSAHS diagnosis, known as polysomnography (PSG), is expensive and time consuming. There is evidence suggesting that snore-related sounds (SRS) carry sufficient information to diagnose OSAHS. In this paper we present a technique for diagnosing OSAHS based solely on snore sound analysis. The method comprises a logistic regression model fed with snore parameters derived from its features such as the pitch and total airway response (TAR) estimated using a higher order statistics (HOS)-based algorithm. Pitch represents a time domain characteristic of the airway vibrations and the TAR represents the acoustical changes brought about by the collapsing upper airways. The performance of the proposed method was evaluated using the technique of K-fold cross validation, on a clinical database consisting of overnight snoring sounds of 41 subjects. The method achieved 89.3% sensitivity with 92.3% specificity (the area under the ROC curve was 0.96). These results establish the feasibility of developing a snore-based OSAHS community-screening device, which does not require any contact measurements.

Mixed-phase modeling in snore sound analysis

Obstructive sleep apnea (OSA) is a highly prevalent disease in which upper airways are collapsed during sleep, leading to serious consequences. The gold standard of diagnosis, called Polysomnography (PSG), requires a full-night hospital stay connected to over 15 channels of measurements requiring physical contact with sensors. PSG is expensive and unsuited for community screening. Snoring is the earliest symptom of OSA, but its potential in OSA diagnosis is not fully recognized yet. In this paper, we propose a novel model for SRS as the response of a mixed-phase system (total airways response, TAR) to a source excitation at the input. The TAR/source model is similar to the vocal tract/source model in speech synthesis, and is capable of capturing acoustical changes brought about by the collapsing upper airways in OSA. We propose an algorithm based on higher-order-spectra (HOS) to jointly estimate the source and TAR, preserving the true phase characteristics of the latter. Working on a clinical database of signals, we show that TAR is indeed a mixed-phased signal and second-order statistics cannot fully characterize it. Night-time speech sounds can corrupt snore recordings and pose a challenge to snore based OSA diagnosis. We show that the TAR could be used to detect speech segments embedded in snores, and derive features to diagnose OSA via non-contact, low-cost instrumentation holding potential for a community screening device.

Higher-order spectra for the estimation of total-airway-response (TAR) in snore-based diagnosis of apnoea

Obstructive sleep apnoea (OSA) is a serious disease caused by the collapse of upper airways during sleep. Untreated OSA is a public health concern. However, over 90% patients remain undiagnosed at present due to the unavailability of a convenient diagnostic tool. Snoring is the earliest and the most prevalent symptom of OSA. In this paper, we model snore related sounds as the response of a non-minimum phase filter (total airways response, TAR) to a source excitation at the input. Based on higher-order statistics of snore sounds, we estimate the TAR and the properties of the source excitation. The TAR/source model is similar to the vocal tract/source model in speech synthesis, and is capable of capturing acoustical changes brought about by the collapsing upper airways in OSA. We show that snore sounds provide an excellent framework for noncontact diagnosis of OSA suitable for development as a population mass screening technique.

Pitch/airway-response and cepstral analysis of snore sounds for the non-contact screening of sleep apnea

Snoring is the earliest and the most frequent symptom of Obstructive Sleep Apnea (OSA), which is a serious disease with a high community prevalence rate. The standard method of OSA diagnosis requires an overnight stay in a sleep lab, connected to over 15 channels of contact-measurements. There is evidence suggesting that Snore-Related-Sounds (SRS) carry sufficient information to diagnose OSA. Snore-based technology opens up opportunities for community-screening devices that do not depend on contact instrumentation. A new technique of diagnosing OSA based solely on multi-parametric snore sound analysis is presented in this paper. The method comprises of a logistic regression model fed with a range of snore parameters derived from its features, the pitch and the Total Airways Response (TAR) estimated using a Higher Order Statistics (HOS) based algorithm. The model was developed and its performance validated on a clinical database consisting of overnight snoring sounds of 41 subjects. Leaveone-out technique was used for validating the model. The validation process achieved 89.3% sensitivity with 92.3% specificity (area under the Receiver Operating Characteristic (ROC) curve was 0.96) in classifying the data sets into the two groups OSA and non-OSA. These results are superior to the existing results and unequivocally illustrate the feasibility of developing a snore-based OSA screening device.

Dynamic Data Analysis in Obstructive Sleep Apnea

Obstructive Sleep Apnea (OSA) is a serious disease caused by the collapse of upper airways during sleep. The present method of measuring the severity of OSA is the Apnea Hypopnea Index (AHI). The AHI is defined as the average number of Obstructive events (Apnea and Hypopnea, OAH-events) during the total sleep period. The number of occurrence of OAH events during each hour of sleep is a random variable with an unknown probability density function. Thus the measure AHI alone is insufficient to describe its true nature. We propose a new measure Dynamic Apnea Hypopnea Index Time Series (DAHI), which captures the temporal density of Apnea event over shorter time intervals, and use its higher moments to obtain a dynamic characterization of OSA

Left-right information flow in the brain during EEG arousals

In disorders such as sleep apnea, sleep is fragmented with frequent EEG-arousal (EEGA) as determined via changes in the sleep-electroencephalogram. EEGA is a poorly understood, complicated phenomenon which is critically important in studying the mysteries of sleep. In this paper we study the information flow between the left and right hemispheres of the brain during the EEGA as manifested through inter-hemispheric asynchrony (IHA) of the surface EEG. EEG data (using electrodes A1/C4 and A2/C3 of international 10-20 system) was collected from 5 subjects undergoing routine polysomnography (PSG). Spectral correlation coefficient (R) was computed between EEG data from two hemispheres for delta-delta(0.5-4 Hz), theta-thetas(4.1-8 Hz), alpha-alpha(8.1-12 Hz) & beta-beta(12.1-25 Hz) frequency bands, during EEGA events. EEGA were graded in 3 levels as (i) micro arousals (3-6 s), (ii) short arousals (6.1-10 s), & (iii) long arousals (10.1-15 s). Our results revealed that in beta band, IHA increases above the baseline after the onset of EEGA and returns to the baseline after the conclusion of event. Results indicated that the duration of EEGA events has a direct influence on the onset of IHA. The latency (L) between the onset of arousals and IHA were found to be L=2plusmn0.5 s (for micro arousals), 4plusmn2.2 s (short arousals) and 6.5plusmn3.6 s (long arousals)

Mixed-phase modeling of snore sounds within a nonlinear framework for component identification

Summary form only given. Snoring is the earliest and the most prevalent symptom of obstructive sleep apnea (OSA), a serious disease caused by the collapse of upper airways during sleep. In this paper, we model snore related sounds (SRS) as the response of a mixed-phase system (total airways response, TAR) to a source excitation at the input. The TAR/source model is similar to the vocal tract/source model in speech synthesis, and is capable of capturing acoustical changes brought about by the collapsing upper airways in OSA. To estimate components of the TAR/source model, preserving true phase information, we develop a novel non-linear framework based on higher-order statistics (HOS). Working on a clinical database of signals, we show that TAR is indeed a mixed-phased signal, and thus correlation (power spectrum) based conventional techniques cannot completely describe snoring sounds.

Comparing benign snores with apneic snores based on high frequency analysis

Snoring is the most common symptom of Obstructive Sleep Apnea (OSA). Several researchers have re ported differences in the power spectrum of both benign and apneic snorers. Conventionally, the frequency band analyzed was less than 5kHz. In this paper, we analyze the snore sound (SS) considering the spectrum at the high frequency band (HFB) 5kHz to 10kHz. We show the existence of a significant difference between 12 benign snoreres (Respiratory Disturbance Index, RDI=4.9±2.4 event/h; 1352 episodes) and 12 Apneic snoreres (RDI=34.7±23.5 event/h; 2153 episodes) on the HFB. Based on this observation, we propose a novel measure P for snore-based OSA screening. The developed measure could separate the 24-subject training data set into apnea/non apnea classes at sensitivity 83.3% and specificity 83.3%. These numbers suggest that HFB carries information that could be valuable for the classification of benign and apneic snorers compared to other band (below 5 kHz) used in the conventional work.

Effect of background sound and impact of snore episode length normalization on snore-based apnea diagnosis

Obstructive Sleep Apnea (OSA) is a serious sleep disorder. OSA is commonly associated with snoring but it is not fully utilized in diagnosis. Snoring contains pseudoperiodic (“pitch of snoring”) packets of energy that produces the characteristic vibrating sounds familiar to us. Our hypothesis is that the pitch of snoring carries information on the state of the upper airways enabling us to characterize it. Snore Related Sounds (SRS) have the advantage as they can be acquired via non-contact measurements cheaply. However, in practice, it is likely that SRS may be corrupted by background interference such as bed sounds, duvet sounds and speech sounds (collectively referred to as “Other Sounds”, OS).