Detection of apneic events from single channel nasal airflow using 2nd derivative method

Detection of sleep apnea is one of the major tasks in sleep studies. Several methods, analyzing the various features of bio-signals, have been applied for automatic detection of sleep apnea, but it is still required to detect apneic events efficiently and robustly from a single nasal airflow signal under varying situations. This study introduces a new algorithm that analyzes the nasal airflow (NAF) for the detection of obstructive apneic events. It is based on mean magnitude of the second derivatives (MMSD) of NAF, which can detect respiration strength robustly under offset or baseline drift. Normal breathing epochs are extracted automatically by examining the stability of SaO(2) and NAF regularity for each subject. The standard MMSD and period of NAF, which are regarded as the values at the normal respiration level, are determined from the normal breathing epochs. In this study, 24 Polysomnography (PSG) recordings diagnosed as obstructive sleep apnea (OSA) syndrome were analyzed. By analyzing the mean performance of the algorithm in a training set consisting of three PSG recordings, apnea threshold is determined to be 13% of the normal MMSD of NAF. NAF signal was divided into 1-s segments for analysis. Each segment is compared with the apnea threshold and classified into apnea events if the segment is included in a group of apnea segments and the group satisfies the time limitation. The suggested algorithm was applied to a test set consisting of the other 21 PSG recordings. Performance of the algorithm was evaluated by comparing the results with the sleep specialist's manual scoring on the same record. The overall agreement rate between the two was 92.0% (kappa=0.78). Considering its simplicity and lower computational load, the suggested algorithm is found to be robust and useful. It is expected to assist sleep specialists to read PSG more quickly and will be useful for ambulatory monitoring of apneas using airflow signals.     

Detection and classification of sleep apnea using genetic algorithms and SVM‐based classification of thoracic respiratory effort and oximetric signal features

Sleep apnea is a relatively prevalent breathing disorder characterized by temporary interruptions in airflow during sleep. There are 2 major types of sleep apnea. Obstructive sleep apnea occurs when air cannot flow through the upper airway despite efforts to breathe. Central sleep apnea occurs when the brain fails to signal to the muscles to maintain breathing. The standard diagnostic test is polysomnography, which is expensive and time consuming. The aim of this study was to design an automatic diagnostic and classifying algorithm for sleep apneas employing thoracic respiratory effort and oximetric signals. This algorithm was trained and tested applying a database of 54 subjects who had undergone polysomnography. A feature extraction stage was conducted to compute features. An optimal genetic algorithm was applied to select optimal features of these 2 kinds of signals. The classification technique was based on the support vector machine classifier to classify the selected features in 3 classes as healthy, obstructive, and central sleep apnea events. The results show that our automated classification algorithm can diagnose sleep apnea and its types with an average accuracy level of 90.2% (87.5‐95.8) in the test set and 90.9% in the validation set with high acceptable accuracy.     

Classification of nasal inspiratory flow shapes by attributed finite automata.

In a significant proportion of individuals, the physiologic decrease of muscle tone during sleep results in increased collapsibility of the upper respiratory airway. At peak inspiratory flow, the pharyngeal soft tissues may collapse and cause airflow limitation or even complete occlusion of the upper airway (sleep apnea). While there are plenty of methods to detect sleep apnea, only a few can be used to monitor flow limitation in sleeping individuals. Nasal prongs connected to pressure sensor provide information of the nasal airflow over time. This paper documents a method to automatically classify each nasal inspiratory pressure profile into one without flow limitation or six flow-limited ones. The recognition of the sample signals consists of three phases: preprocessing, primitive extraction, and word parsing phases. In the last one, a sequence of signal primitives is treated as a word and we test its membership in the attribute grammars constructed to the signal categories. The method gave in practical tests surprisingly high performance. Classifying 94;pc of the inspiratory profiles in agreement with the visual judgment of an expert physician, the performance of the method was considered good enough to warrant further testing in well-defined patient populations to determine the pressure profile distributions of different subject classes.     

基于深度图像的非接触式呼吸检测算法研究

呼吸是人的基本生命活动,监测呼吸可以得知呼吸道和胸廓运动的生理、病理学状态,对某些呼吸系统疾病的诊断有重要的参考价值;提出了一种非接触式呼吸监测方法:对红外视频流中的每帧胸腹部区域数据进行降维,计算所有胸腹部区域数据的方差,将一定时间段内的方差序列进行低通滤波;最后根据方差序列可以获得该段时间内的呼吸频率和呼吸暂停时间;提出的非接触式呼吸检测算法在不影响被监测者正常睡眠活动的情况下,可以准确获取呼吸频率与其他相关参数,为健康监测和相关疾病的诊断提供了数据支持;日常家居场景的实验中,检测到的呼吸次数与实际完全一致,并且与实际胸腹部起伏变化基本同步,较好的保证了结果的准确性。     

Detection of high-frequency respiratory movements during sleep

Sleep-related breathing disorders are common in adults and they have a significant impact on vigilance and quality of life. Previous studies have shown the validity of the static-charge-sensitive bed (SCSB) in monitoring breathing abnormalities during sleep. A whole nights sleep study produces a signal with considerable length, and therefore an automated analysis system would be of great need. In this work we focus on detection of high-frequency respiratory movement (HFRM) patterns which are related to increased respiratory efforts. The paper documents four methods to automatically detect these patterns. The first two are based on classical statistical tests applied to the SCSB signal, and the other two use spectral characteristics in order to adaptively segment the SCSB signal. Finally we adjust each method to detect patterns that coincide with the HFRMs determined by an expert, and evaluate the performance of the methods using independent test data.     

A new scheme for reducing breathing trouble through MEMS based capacitive pressure sensor

In this paper, a treatment of respiratory disorders with brushless DC motor (BLDC) driven positive airway pressure (PAP) respirator is developed. The proposed schema of the system consists of a BLDC motor driven blower fan aided by a MEMS capacitive type pressure sensor to measure respiration rate (RR). To measure the respiration rate, the array of such sensors are mounted below right nostril (RN) and left nostril (LN), in such a way that the nasal airflow during inspiration and expiration impinge on the sensor diaphragms directly. Due to irregularities in nasal airflow in some respiratory diseases, the RR varies from the normal rate (12–20). Thus, a supporting airflow regulatory system has been designed to reduce abnormalities in RR. The supporting system consists of a positive airway pressure (PAP) respirator with a blower fan to relieve patients breathing abnormalities. The MEMS based RR sensors help to monitor patients breathing rate continuously and finally maintain the required air pressure/flow by regulating the rpm of the blower fan through BLDC motor drive. In order to implement such a control action, we have chosen the sensorless drive of BLDC motor to construct a transportable as well as noise immune system. An algorithm has been developed to sustain normal RR for both bradypnea (RR < 12) and trachypnea (RR > 20), which puts into operation through ATmega 328 to facilitate high level precision controlled action. The control system alongwith the sensory part occupies limited space in few centimeters with light weight. As a result, the electronics of the whole system can be easily mounted at the outer surface of the tube connected with the nasal mask. The scheme of such a portable and cost effective system is described in this present work.     

基于声音采集方案的睡眠呼吸监测系统设计

睡眠-呼吸暂停综合症危及人体呼吸睡眠质量,影响人体血液氧含量,加重人体大脑、肌肉等组织缺氧风险。临床上,传统呼吸暂停综合征治疗中,由于时间和场地限制,医生往往只能根据病人或其家属口述判断病情,无法对患者的呼吸状况及治疗方案效果做出直观的评价。为了方便记录患者睡眠呼吸状况,提出了一种基于声音采集方案的睡眠呼吸监测系统,以驻极体式声音传感器为采样前端,结合STM32平台和Fatfs文件系统实现呼吸声音的采集和存储,采用阈值分割法借助Matlab进行数据处理。结果表明,本系统可实现对监测数据的存储、读取、分析和波形显示。该系统便于使用、精度高、工作稳定可靠,可直观的反映出病人睡眠呼吸状况,呼吸频率计算值与实际值误差在10%以内,具有较高的临床应用价值。     

非入侵式睡眠呼吸监测系统的设计与实现

根据养老院、医院等特殊区域人群的睡眠呼吸监护需求,设计了非入侵式柔性压感睡眠呼吸监测系统。系统通过硬件电路设计,采集人体睡眠时的呼吸信号,并进行消噪、去趋势等预处理。在硬件终端中通过呼吸信号的幅度和周期的特征区分呼吸类别,并实时判断是否发生了呼吸暂停,记录暂停的时刻与持续时长,并将数据通过蓝牙传至手机,在手机APP上可绘制实时波形,手机把数据上传至云平台。PC端软件可从云平台获取数据,绘制拟合呼吸信号曲线,判定记录睡眠数据。经实验测试,系统判定呼吸次数与实际基本一致,并可准确判断呼吸暂停情况,满足长程实现睡眠呼吸监测的要求。     

Computerized acoustic detection of obstructive apnea

Cardiac, respiratory and neurologic abnormalities have been identified as causes of Sudden Infant Death Syndrome (SIDS). Recurrent central apnea (no respiratory effort or nasal/oral airflow) and obstructive apnea (respiratory effort without concurrent nasal/oral airflow) in infants are considered risk factors for SIDS. However, using currently available monitoring techniques, normal activities such as yawns, stretches and swallows cannot be distinquished from short obstructive episodes lasting less than 20 s. A system was developed to more accurately detect obstructive apnea in infants using a miniature microphone placed over the trachea, a cassette tape recorder and a MINC-11 microcomputer. Respiratory sounds were recorded on 5 anesthesized rabbits in which partial and total airway obstruction was artificially induced. Sounds were analyzed by computer using fast Fourier transformations. Amplitude versus frequency was plotted for normal breathing, partial obstruction and total obstruction. Characteristic patterns were identified for each episode demonstrating that acoustic detection of apnea in infants by a microprocessor-based monitor is feasible.     

基于RFID标签阵列的睡眠期间呼吸量连续监测系统

睡眠期间连续且准确的呼吸量监测有助于推断用户的睡眠阶段以及提供一些慢性疾病的线索。现有工作主要针对呼吸频率进行感知和监测,缺乏对呼吸量进行连续监测的手段。针对上述问题提出了一种基于商用无线射频识别(RFID)标签的无线感知用户睡眠期间呼吸量的系统——RF-SLEEP。RF-SLEEP通过阅读器连续收集附着在胸部表面的标签阵列返回的相位值及时间戳数据,计算出呼吸引起的胸部不同点的位移量,基于广义回归神经网络(GRNN)构建胸部不同点的位移量与呼吸量之间的关系模型,从而实现对用户睡眠期间呼吸量的评估。RF-SLEEP通过在用户肩膀处附着双参考标签,消除用户睡眠期间翻转身体对胸部位移计算造成的误差。实验结果表明,RFSLEEP对不同用户睡眠期间的呼吸量连续监测的平均精确度为92.49%。     

Automated sleep stage scoring using hybrid rule- and case-based reasoning.

We propose an automated method for sleep stage scoring using hybrid rule- and case-based reasoning. The system first performs rule-based sleep stage scoring, according to the Rechtschaffen and Kale's sleep-scoring rule (1968), and then supplements the scoring with case-based reasoning. This method comprises signal processing unit, rule-based scoring unit, and case-based scoring unit. We applied this methodology to three recordings of normal sleep and three recordings of obstructive sleep apnea (OSA). Average agreement rate in normal recordings was 87.5% and case-based scoring enhanced the agreement rate by 5.6%. This architecture showed several advantages over the other analytical approaches in sleep scoring: high performance on sleep disordered recordings, the explanation facility, and the learning ability. The results suggest that combination of rule-based reasoning and case-based reasoning is promising for an automated sleep scoring and it is also considered to be a good model of the cognitive scoring process.     

一种仿生感觉毛气流传感器

模仿昆虫感觉毛的结构,设计制备了表面对称电极含金属芯PVDF气流传感器SMPF(Symmetric Metal core PVDF Fiber).利用自制的拉制纤维设备,制备了SMPF胚体.在表面涂镀对称电极后,经过高温极化、电极封装等工艺后,成功制备了SMPF气流传感器.基于第1类压电方程和流体力学理论,建立了悬臂梁结构的SMPF气流传感模型,分析了传感器输出信号与纤维长度、气流速度以及气流作用方向之间的关系.将悬臂梁结构的SMPF安置在气流流场中,进行冲击气流测试实验.实验结果表明,SMPF气流传感器的输出信号与纤维长度成非线性关系,与气流速度成平方关系,与气流作用方向成"8"字形关系.实验结果验证了理论模型,表明SMPF传感器能够感知气流的速度和作用方向,具有较广泛的工程应用前景.     

多种姿态下的人体呼吸率视觉检测

呼吸率是衡量人体健康状况的重要指标之一.针对现有呼吸率检测方法存在人体受测姿态单一、准确率低和鲁棒性差的问题,提出适用于多种姿态下的人体呼吸率视觉检测方法.该方法使用普通摄像机拍摄人体呼吸视频.首先,利用图像金字塔光流法处理视频连续图像得到运动前景区域,将其中最大连通区域初步认定为胸腹呼吸区域.然后,将视频每一帧图像的呼吸区域输入复可控金字塔进行多尺度多方向空间分解,得到多个尺度多个方向的幅度谱和相位谱.在此基础上将每一帧的多个尺度多个方向相位谱用幅度谱加权后进行平均得到相位-时间信号.最后,对提取的信号进行判断,若信号主频在呼吸信号频带范围内且能量占比高则对该信号通过峰值检测得到呼吸率,否则重新选取视频连续图像进行后续检测.实验结果表明,本文方法适用于人体多种姿态下的呼吸率检测,在准确率和鲁棒性上优于现有方法.     

Modelling droplet motion and interfacial tension in filters collecting liquid aerosols

Extensive experimental investigations have shown some of the differences between the behaviours of the barrel and the clamshell shapes of droplets on filter fibres in flow fields. Realistic flow velocities (such as those used in many industrial filter systems) were utilised. The forces acting are air drag, interfacial tension and gravity. The properties of the interfacial restoring force are modelled, and show agreement with the experimental results, at least in the linear extension region before the onset of oscillatory behaviour of the droplets (induced by instability of the flow field). The model for the oscillatory behaviour is explored, and the natural frequencies of oscillation in the radial and transverse directions are shown to be the same, for the barrel shape. The clamshell shape also has the same natural frequencies, but they are different to those of the barrel shape. The coupling of the radial and transverse oscillation modes is explored for both the barrel and clamshell shape. Some contact angle results are given, both without airflow acting on the droplet and with increasing airflow.     

An expert system for automated recognition of patients with obstructive sleep apnea using electrocardiogram recordings

Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder. The traditional diagnosis methods of the disorder are cumbersome and expensive. The ability to automatically identify OSA from electrocardiogram (ECG) recordings is important for clinical diagnosis and treatment. In this study, we proposed an expert system based on discrete wavelet transform (DWT), fast-Fourier transform (FFT) and least squares support vector machine (LS-SVM) for the automatic recognition of patients with OSA from nocturnal ECG recordings. Thirty ECG recordings collected from normal subjects and subjects with sleep apnea, each of approximately 8 h in duration, were used throughout the study. The proposed OSA recognition system comprises three stages. In the first stage, an algorithm based on DWT was used to analyze ECG recordings for the detection of heart rate variability (HRV) and ECG-derived respiration (EDR) changes. In the second stage, an FFT based power spectral density (PSD) method was used for feature extraction from HRV and EDR changes. Then, a hill-climbing feature selection algorithm was used to identify the best features that improve classification performance. In the third stage, the obtained features were used as input patterns of the LS-SVM classifier. Using the cross-validation method, the accuracy of the developed system was found to be 100% for using a subset of selected combination of HRV and EDR features. The results confirmed that the proposed expert system has potential for recognition of patients with suspected OSA by using ECG recordings.     

Fuzzy reasoning used to detect apneic events in the sleep apnea-hypopnea syndrome

The sleep apnea/hypopnea syndrome is a very common sleep disorder, characterised by disrupted breathing during sleep. Depending on the extent of the disruptions to sleep, these are classified as apneas or hypopneas. In order to locate these apneic events an analysis of respiratory signals recorded for an entire night’s sleep is necessary. However, identifying and classifying apneic events is a complex task, given the error associated with the process for digitising signals, variability in expert criteria and the complexity of the signals themselves. This article describes a fuzzy-logic-based automated system for detecting apneic events and classifying them as apneas or hypopneas. The aim is to equip this system with mechanisms for dealing with imprecision and reasoning affected by uncertainty. The ultimate goal was to assist the physician in diagnosing the sleep apnea/hypopnea syndrome. Results in terms of locating events in the polysomnogram showed sensitivity and specificity of 0.87 and 0.89, respectively. A receiver operating curve index of 0.88 was obtained for the classification of events as apneas or hypopneas.     

Positive pressure breathing during rest and exercise

The requirements to maintain a positive pressure with respiratory protection during heavy exercise and the effects on ventilation and feelings of discomfort were investigated. Eight male subjects participated, using the respirator system during rest and exercise at about 80% of their individual maximum power. A blower was used at maximum and medium capacity and at two pressure levels (3 and 15 mbar). Additionally, the mouth pressure was used as a feedback for the blower. The blower decreased the fraction of the breathing cycle with negative pressures from 50% (SD 4%) to 15% (SD 10%) during exercise. Negative pressures occurred at all settings of the blower during exercise. Thus, the currently available commercial blower systems do not supply a sufficient airflow to maintain a positive pressure during heavy exercise. Positive pressure breathing did not affect the ventilation and the circulation. But the oxygen consumption was higher with the blower and respirator than without.     

RESP-24: a computer program for the investigation of 24-h breathing abnormalities in heart failure patients

In this paper, we describe a computer program (RESP-24) specifically devised to assess the prevalence and characteristics of breathing disorders in ambulant chronic heart failure patients during the overall 24 h period. The system works on a single channel respiratory signal (RS) recorded through a Holter-like portable device. In the pre-processing stage RESP-24 removes noise, baseline drift and motion artefacts from the RS using a non-linear filter, enhances respiratory frequency components through high-pass filtering and derives an instantaneous tidal volume (ITV) signal. The core processing is devoted to the identification and classification of the breathing pattern into periodic breathing (PB), normal breathing or non-classifiable breathing using a 60 s segmentation, and to the identification and estimation of apnea and hypopnea events. Sustained episodes of PB are detected by cross analysis of both the spectral content and time behavior of the ITV signal. User-friendly interactive facilities allow all the results of the automatic analysis procedure to be edited. The final report provides a set of standard and non-standard parameters quantifying breathing abnormalities during the 24 h period, the night-time and the day-time, including the apnea/hypopnea index, the apnea index, the total time spent in apnea or in hypopnea and the prevalence of non-apneic and apneic PB. The accuracy of these measurements was appraised on a data set of 14 recordings, by comparing them with those provided by a trained analyst. The mean and standard deviation of the error of the automatic procedure were below respectively 6 and 8% of the reference value for all parameters considered and the mean total classification accuracy was 92%. In most cases, the individual error was <12%. We conclude that measurements provided automatically by the RESP-24 software are suitable for screening purposes and clinical trials, although a preventive check of signal quality should be recommended.     

Catheter sensor system for in-situ breathing and optical imaging measurements at airway in inside of lung

A catheter sensor system composed of a tube flow sensor with a medical basket forceps and an optical fiberscope was systemized for in-situ measurements in the airway in the lung system. The tube flow sensor was produced by assembling the sensor film containing two heaters onto the tube surface, and the basket forceps was installed into the inside space of the tube sensor. The assembled tube flow sensor with the basket forceps was inserted into the tube and was fixed at the center of the tube by expanding the basket. The flow detection characteristics of the tube flow sensor were experimentally evaluated. A calibration equation based on King’s law was derived from the sensor output vs. flow velocity curve, and a sufficiently short response time of 60 ms was obtained for the breathing measurements in a rabbit and a person. Finally, the tube flow sensor with the basket forceps and the optical fiberscope was systemized into a single tube with the diameter of 5.0 mm for in-situ measurements in the airway. The developed system successfully detected both a breathing airflow waveform and an optical image inside the airway in the rabbit.

     

Micro-machined respiratory monitoring system development for artificial ventilator in animal experiment

We developed a respiratory monitoring system to evaluate elasticity on the lungs of small animals by the positive-pressure airflow under artificial ventilation during experiments. The system consists of a tube-type thermal flow sensor fabricated using microelectromechanical systems (MEMS) technology and commercially available Si-MEMS pressure sensors. We first used a small spherical balloon having an inner volume of 0.68 cc as a simulated lung. We evaluated the balloon elasticity from the supplied flow volume and pressure inside the balloon and confirmed that our system can detect balloon elasticity from the gradient under both static and cyclic airflow. We evaluated our system in terms of the lung elasticity of a rat and obtained a flow volume vs. pressure curve showing the lung elasticity under artificial ventilation. The changes in the flow rate and pressure waveforms due to airway contraction with drug administration were detected with our system in real time.