Toward prediction of physiological state signals in sleep apnea

Bock, Joel R.; Gough, David

doi:10.1109/10.725330

Cited by 37 publications

(29 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, a small number of nonlinear dimensional analyses of respiration have been reported previously. BOCK et al [20] reported that, by analysing the largest Lyapunov exponent and correlation dimension, the respiratory state in sleeping patients with apnoea could be shown to have chaotic dynamics. The current authors have previously shown that respiratory movement in patients with severe OSAHS during apneoic sleep was random, as no D2 for respiratory movement during sleep with apnoea could be obtained [13].…”

Section: Analysis Of the Dimensionality For Respiratory Movementmentioning

confidence: 99%

A short daytime test using correlation dimension for respiratory movement in OSAHS

Miyata

Burioka

Sako³

et al. 2004

Eur Respir J

View full text Add to dashboard Cite

In order to examine the pathology in patients with obstructive sleep apnoea/hypopnoea syndrome (OSAHS), the nonlinear properties of respiratory movement and breath-to-breath variations during resting wakefulness with eyes closed was investigated.Recording of the respiratory movement using inductive plethysmography was performed on 14 patients with OSAHS and 13 control subjects for 2 h in the supine position during daytime. To calculate the correlation dimension (D2) for respiratory movement, an algorithm proposed by Grassberger and Procaccia was applied. The indices of breath-to-breath variations were estimated. To calculate D2 and breath-tobreath variations, two different segments were selected (200 s each).The value of D2 for respiratory movement in patients with OSAHS was significantly greater than that in control subjects. In the case of o2.0 of D2 for respiratory movement, the sensitivity and specificity of detecting the presence of OSAHS was 85.7% and 76.9%, respectively. On the basis of breath-to-breath variations, only the coefficient of variation of expiratory time for respiratory movement in patients with OSAHS was significantly greater than that in the control subjects.In conclusion, the measurements of correlation dimensions for respiratory movement with a brief period during wakefulness may be a useful index for identifying patients with obstructive sleep apnoea/hypopnoea syndrome. Eur Respir J 2004; 23: 885-890.

show abstract

Section: Analysis Of the Dimensionality For Respiratory Movementmentioning

confidence: 99%

A short daytime test using correlation dimension for respiratory movement in OSAHS

Miyata

Burioka

Sako³

et al. 2004

Eur Respir J

View full text Add to dashboard Cite

show abstract

“…When the total lengths of the apnea and hypopnea periods are calculated, the consecutive and events must be joined, respectively. Many authors have pointed out the nonlinearity of cardio-respiratory signals [17], and used different types of artificial neural networks (ANNs) for their processing [18], [19]. We propose four different ANNs for time-domain respiration pattern classification.…”

Section: B Design Considerationsmentioning

confidence: 99%

A novel method for the detection of apnea and hypopnea events in respiration signals

Varady

Micsik

Benedek³

et al. 2002

IEEE Trans. Biomed. Eng.

173

View full text Add to dashboard Cite

Abstract-The monitoring of breathing dynamics is an essential diagnostic tool in various clinical environments, such as sleep diagnostics, intensive care and neonatal monitoring. This paper introduces an innovative signal classification method that is capable of on-line detection of the presence or absence of normal breathing. Four different artificial neural networks are presented for the recognition of three different patterns in the respiration signals (normal breathing, hypopnea, and apnea). Two networks process the normalized respiration signals directly, while another two use sophisticatedly preprocessed signals. The development of the networks was based on training sets from the polysomnographic records of nine different patients. The detection performance of the networks was tested and compared by using up to 8000 untrained breathing patterns from 16 different patients. The networks which classified the preprocessed respiration signals produced an average detection performance of over 90%. In the light of the moderate computational power used, the presented method is not only viable in clinical polysomnographs and respiration monitors, but also in portable devices.

show abstract

“…The apneas in sleep can be classified into three types: 1) obstructive apnea, where the pharynx becomes occluded and eventually collapses; 2) central apnea, caused by fluctuations in central respiratory control; and 3) mixed disturbances, where aspects of both obstructive and central apneas are present (Silage 1990;Bock et al, 1998). In particular, the major cause of the OSA symptom (Behbehani et al, 1995;Yen et al , 1997;Favre et al, 2003;Tsai et al, 2008) is that a patient's airflow ceases because the pharyngeal wall collapses in sleep.…”

Section: Introductionmentioning

confidence: 97%

“…To diagnose OSA or other apneas, researchers have employed polysomnographic recordings that may include electrocardiogram, electroencephalogram, electrooculogram, or electromyogram measures of respiration, and arterial oxygen saturation (Bock and Gough, 1998). However, such recordings are always Downloaded by [The University of Manchester Library] at 05:20 09 October 2014 time-consuming.…”

Section: Introductionmentioning

confidence: 99%

Adaptive pressure tracking and breathing period prediction for obstructive sleep apnea treatment respirators with bi‐level positive airway pressure

Tsai

Wang

Chen

et al. 2010

Journal of the Chinese Institute of Engineers

View full text Add to dashboard Cite

This paper presents techniques for adaptive pressure tracking and breathing period prediction in an obstructive sleep apnea (OSA) treatment system by means of bilevel positive airway pressure (BiPAP). In order to achieve bi-level pressure tracking, a closed-loop high-speed DC brushless motor together with a blower and an airway module was constructed by a proportional-integral-derivative (PID) velocity controller, which was then implemented into a low-cost digital signal processor (DSP) on a Microchip. With this controlled closed-loop airway module, a mathematical model of the overall open-loop system was established based on the input-output data and its system parameters were sequentially determined using the recursive least-squares (RLS) approach. An adaptive pressure tracking controller, including a nonlinear feedforward controller and a gain scheduling PID feedback controller, was proposed to follow desired bi-level pressure setpoints. Three breathing prediction methods are presented to estimate the incoming breathing period, including inhalation and exhalation, in order to automatically provide appropriate inhalation time for the BiPAP respirator. Through experimental results, the proposed control system, together with the proposed breathing period prediction methods, is shown effective and useful in achieving satisfactory bi-level airway pressure tracking by following human breathing conditions.

show abstract

Toward prediction of physiological state signals in sleep apnea

Cited by 37 publications

References 30 publications

A short daytime test using correlation dimension for respiratory movement in OSAHS

A short daytime test using correlation dimension for respiratory movement in OSAHS

A novel method for the detection of apnea and hypopnea events in respiration signals

Adaptive pressure tracking and breathing period prediction for obstructive sleep apnea treatment respirators with bi‐level positive airway pressure

Contact Info

Product

Resources

About