Screening of patients with Obstructive Sleep Apnea Syndrome using C4.5 algorithm based on non linear analysis of respiratory signals during sleep

Sleep apnea: a review of diagnostic sensors, algorithms, and therapies

While public awareness of sleep related disorders is growing, sleep apnea syndrome (SAS) remains a public health and economic challenge. Over the last two decades, extensive controlled epidemiologic research has clarified the incidence, risk factors including the obesity epidemic, and global prevalence of obstructive sleep apnea (OSA), as well as establishing a growing body of literature linking OSA with cardiovascular morbidity, mortality, metabolic dysregulation, and neurocognitive impairment. The US Institute of Medicine Committee on Sleep Medicine estimates that 50-70 million US adults have sleep or wakefulness disorders. Furthermore, the American Academy of Sleep Medicine (AASM) estimates that more than 29 million US adults suffer from moderate to severe OSA, with an estimated 80% of those individuals living unaware and undiagnosed, contributing to more than $149.6 billion in healthcare and other costs in 2015. Although various devices have been used to measure physiological signals, detect apneic events, and help treat sleep apnea, significant opportunities remain to improve the quality, efficiency, and affordability of sleep apnea care. As our understanding of respiratory and neurophysiological signals and sleep apnea physiological mechanisms continues to grow, and our ability to detect and process biomedical signals improves, novel diagnostic and treatment modalities emerge.

OBJECTIVE

This article reviews the current engineering approaches for the detection and treatment of sleep apnea.

APPROACH

It discusses signal acquisition and processing, highlights the current nonsurgical and nonpharmacological treatments, and discusses potential new therapeutic approaches.

MAIN RESULTS

This work has led to an array of validated signal and sensor modalities for acquiring, storing and viewing sleep data; a broad class of computational and signal processing approaches to detect and classify SAS disease patterns; and a set of distinctive therapeutic technologies whose use cases span the continuum of disease severity.

SIGNIFICANCE

This review provides a current perspective of the classes of tools at hand, along with a sense of their relative strengths and areas for further improvement.

Evaluation of a Decision Support System for Obstructive Sleep Apnea with Nonlinear Analysis of Respiratory Signals

Introduction

Obstructive Sleep Apnea (OSA) is a common sleep disorder requiring the time/money consuming polysomnography for diagnosis. Alternative methods for initial evaluation are sought. Our aim was the prediction of Apnea-Hypopnea Index (AHI) in patients potentially suffering from OSA based on nonlinear analysis of respiratory biosignals during sleep, a method that is related to the pathophysiology of the disorder.

Materials and Methods

Patients referred to a Sleep Unit (135) underwent full polysomnography. Three nonlinear indices (Largest Lyapunov Exponent, Detrended Fluctuation Analysis and Approximate Entropy) extracted from two biosignals (airflow from a nasal cannula, thoracic movement) and one linear derived from Oxygen saturation provided input to a data mining application with contemporary classification algorithms for the creation of predictive models for AHI.

Results

A linear regression model presented a correlation coefficient of 0.77 in predicting AHI. With a cutoff value of AHI = 8, the sensitivity and specificity were 93% and 71.4% in discrimination between patients and normal subjects. The decision tree for the discrimination between patients and normal had sensitivity and specificity of 91% and 60%, respectively. Certain obtained nonlinear values correlated significantly with commonly accepted physiological parameters of people suffering from OSA.

Discussion

We developed a predictive model for the presence/severity of OSA using a simple linear equation and additional decision trees with nonlinear features extracted from 3 respiratory recordings. The accuracy of the methodology is high and the findings provide insight to the underlying pathophysiology of the syndrome.

Conclusions

Reliable predictions of OSA are possible using linear and nonlinear indices from only 3 respiratory signals during sleep. The proposed models could lead to a better study of the pathophysiology of OSA and facilitate initial evaluation/follow up of suspected patients OSA utilizing a practical low cost methodology.

Trial Registration

ClinicalTrials.gov NCT01161381

Lung and brainstem cytokine levels are associated with breathing pattern changes in a rodent model of acute lung injury

Acute lung injury evokes a pulmonary inflammatory response and changes in the breathing pattern. The inflammatory response has a centrally mediated component which depends on the vagi. We hypothesize that the central inflammatory response, complimentary to the pulmonary inflammatory response, is expressed in the nuclei tractus solitarii (nTS) and that the expression of cytokines in the nTS is associated with breathing pattern changes. Adult, male Sprague-Dawley rats (n=12) received intratracheal instillation of either bleomycin (3units in 120μl of saline) or saline (120μl). Respiratory pattern changed by 24h. At 48h, bronchoalveolar lavage fluid and lung tissue had increased IL-1β and TNF-α levels, but not IL-6. No changes in these cytokines were noted in serum. Immunocytochemical analysis of the brainstem indicated increased expression of IL-1β in the nTS commissural subnucleus that was localized to neurons. We conclude that breathing pattern changes in acute lung injury were associated with increased levels of IL-1β in brainstem areas which integrate cardio-respiratory sensory input.

Vagal-dependent nonlinear variability in the respiratory pattern of anesthetized, spontaneously breathing rats

Physiological rhythms, including respiration, exhibit endogenous variability associated with health, and deviations from this are associated with disease. Specific changes in the linear and nonlinear sources of breathing variability have not been investigated. In this study, we used information theory-based techniques, combined with surrogate data testing, to quantify and characterize the vagal-dependent nonlinear pattern variability in urethane-anesthetized, spontaneously breathing adult rats. Surrogate data sets preserved the amplitude distribution and linear correlations of the original data set, but nonlinear correlation structure in the data was removed. Differences in mutual information and sample entropy between original and surrogate data sets indicated the presence of deterministic nonlinear or stochastic non-Gaussian variability. With vagi intact (n = 11), the respiratory cycle exhibited significant nonlinear behavior in templates of points separated by time delays ranging from one sample to one cycle length. After vagotomy (n = 6), even though nonlinear variability was reduced significantly, nonlinear properties were still evident at various time delays. Nonlinear deterministic variability did not change further after subsequent bilateral microinjection of MK-801, an N-methyl-D-aspartate receptor antagonist, in the Kölliker-Fuse nuclei. Reversing the sequence (n = 5), blocking N-methyl-D-aspartate receptors bilaterally in the dorsolateral pons significantly decreased nonlinear variability in the respiratory pattern, even with the vagi intact, and subsequent vagotomy did not change nonlinear variability. Thus both vagal and dorsolateral pontine influences contribute to nonlinear respiratory pattern variability. Furthermore, breathing dynamics of the intact system are mutually dependent on vagal and pontine sources of nonlinear complexity. Understanding the structure and modulation of variability provides insight into disease effects on respiratory patterning.

Toward emotion aware computing: an integrated approach using multichannel neurophysiological recordings and affective visual stimuli

This paper proposes a methodology for the robust classification of neurophysiological data into four emotional states collected during passive viewing of emotional evocative pictures selected from the International Affective Picture System. The proposed classification model is formed according to the current neuroscience trends, since it adopts the independency of two emotional dimensions, namely arousal and valence, as dictated by the bidirectional emotion theory, whereas it is gender-specific. A two-step classification procedure is proposed for the discrimination of emotional states between EEG signals evoked by pleasant and unpleasant stimuli, which also vary in their arousal/intensity levels. The first classification level involves the arousal discrimination. The valence discrimination is then performed. The Mahalanobis (MD) distance-based classifier and support vector machines (SVMs) were used for the discrimination of emotions. The achieved overall classification rates were 79.5% and 81.3% for the MD and SVM, respectively, significantly higher than in previous studies. The robust classification of objective emotional measures is the first step toward numerous applications within the sphere of human-computer interaction.

On the classification of emotional biosignals evoked while viewing affective pictures: an integrated data-mining-based approach for healthcare applications

Recent neuroscience findings demonstrate the fundamental role of emotion in the maintenance of physical and mental health. In the present study, a novel architecture is proposed for the robust discrimination of emotional physiological signals evoked upon viewing pictures selected from the International Affective Picture System (IAPS). Biosignals are multichannel recordings from both the central and the autonomic nervous systems. Following the bidirectional emotion theory model, IAPS pictures are rated along two dimensions, namely, their valence and arousal. Following this model, biosignals in this paper are initially differentiated according to their valence dimension by means of a data mining approach, which is the C4.5 decision tree algorithm. Then, the valence and the gender information serve as an input to a Mahalanobis distance classifier, which dissects the data into high and low arousing. Results are described in Extensible Markup Language (XML) format, thereby accounting for platform independency, easy interconnectivity, and information exchange. The average recognition (success) rate was 77.68% for the discrimination of four emotional states, differing both in their arousal and valence dimension. It is, therefore, envisaged that the proposed approach holds promise for the efficient discrimination of negative and positive emotions, and it is hereby discussed how future developments may be steered to serve for affective healthcare applications, such as the monitoring of the elderly or chronically ill people.