Identification of apnea during respiratory monitoring using support vector machine classifier: a pilot study

To determine the use of photoplethysmography (PPG) as a reliable marker for identifying respiratory apnea based on time–frequency features with support vector machine (SVM) classifier. The PPG signals were acquired from 40 healthy subjects with the help of a simple, non-invasive experimental setup under normal and induced apnea conditions. Artifact free segments were selected and baseline and amplitude variabilities were derived from each recording. Frequency spectrum analysis was then applied to study the power distribution in the low frequency (0.04–0.15 Hz) and high frequency (0.15–0.40 Hz) bands as a result of respiratory pattern changes. Support vector machine (SVM) learning algorithm was used to distinguish between the normal and apnea waveforms using different time–frequency features. The algorithm was trained and tested (780 and 500 samples respectively) and all the simulations were carried out using linear kernel function. Classification accuracy of 97.22 % was obtained for the combination of power ratio and reflection index features using SVM classifier. The pilot study indicates that PPG can be used as a cost effective diagnostic tool for detecting respiratory apnea using a simple, robust and non-invasive experimental setup. The ease of application and conclusive results has proved that such a system can be further developed for use in real-time monitoring under critical care conditions.

[1]  R. Gosling,et al.  Photoplethysmographic assessment of pulse wave reflection: blunted response to endothelium-dependent beta2-adrenergic vasodilation in type II diabetes mellitus. , 1999, Journal of the American College of Cardiology.

[2]  Aymen A. Alian,et al.  Impact of central hypovolemia on photoplethysmographic waveform parameters in healthy volunteers part 2: frequency domain analysis , 2011, Journal of Clinical Monitoring and Computing.

[3]  Yue-Der Lin,et al.  Coherence Analysis between Respiration and PPG Signal by Bivariate AR Model , 2009 .

[4]  L. Nilsson,et al.  Monitoring of respiratory rate in postoperative care using a new photoplethysmographic technique , 2004, Journal of Clinical Monitoring and Computing.

[5]  R.I. Kitney,et al.  Real-time heart rate variability extraction using the Kaiser window , 1997, IEEE Transactions on Biomedical Engineering.

[6]  J. C. Dorlas,et al.  Photo-electric plethysmography as a monitoring device in anaesthesia. Application and interpretation. , 1985, British journal of anaesthesia.

[7]  Nigel H Lovell,et al.  Non-invasive classification of severe sepsis and systemic inflammatory response syndrome using a nonlinear support vector machine: a preliminary study , 2010, Physiological measurement.

[8]  R. Pizov,et al.  Pulse oximetry plethysmographic waveform during changes in blood volume. , 1999, British journal of anaesthesia.

[9]  D. Kass,et al.  Parametric model derivation of transfer function for noninvasive estimation of aortic pressure by radial tonometry , 1999, IEEE Transactions on Biomedical Engineering.

[10]  J. N. Watson,et al.  Developing an algorithm for pulse oximetry derived respiratory rate (RRoxi): a healthy volunteer study , 2012, Journal of Clinical Monitoring and Computing.

[11]  M. Nitzan,et al.  The variability of the photoplethysmographic signal - a potential method for the evaluation of the autonomic nervous system , 1998, Physiological measurement.

[12]  Professor P. Å. Öberg,et al.  Estimation of respiratory volumes from the photoplethysmographic signal. Part 2: a model study , 2006, Medical & Biological Engineering & Computing.

[13]  Y. Mendelson.  Pulse oximetry: theory and applications for noninvasive monitoring. , 1992, Clinical chemistry.

[14]  B. Fetics,et al.  Estimation of Central Aortic Pressure Waveform by Mathematical Transformation of Radial Tonometry Pressure Data , 1998 .

[15]  P. Chowienczyk,et al.  Contour analysis of the photoplethysmographic pulse measured at the finger , 2006, Journal of hypertension.

[16]  M. Arthanari,et al.  Classification of electrocardiogram signals with support vector machines and extreme learning machine , 2011, Neural Computing and Applications.

[17]  A. Johansson,et al.  Monitoring of Heart and Respiratory Rates in Newborn Infants Using a New Photoplethysmographic Technique , 1999, Journal of Clinical Monitoring and Computing.

[18]  D. Sapoznikov,et al.  POWER SPECTRUM ANALYSIS OF SPONTANEOUS FLUCTUATIONS IN THE PHOTOPLETHYSMOGRAPHIC SIGNAL , 1994, Journal of basic and clinical physiology and pharmacology.

[19]  J Bhatia,et al.  Current Options in the Management of Apnea of Prematurity , 2000, Clinical pediatrics.

[20]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[21]  P. Chowienczyk,et al.  Determination of age-related increases in large artery stiffness by digital pulse contour analysis. , 2002, Clinical science.

[22]  Mika P. Tarvainen,et al.  Software for advanced HRV analysis , 2004, Comput. Methods Programs Biomed..

[23]  A. Johansson,et al.  Estimation of respiratory volumes from the photoplethysmographic signal. Part I: experimental results , 2006, Medical & Biological Engineering & Computing.

[24]  C. H. Chen,et al.  Estimation of central aortic pressure waveform by mathematical transformation of radial tonometry pressure. Validation of generalized transfer function. , 1997, Circulation.

[25]  A Calciati,et al.  Autonomic control of skin microvessels: assessment by power spectrum of photoplethysmographic waves. , 1996, Clinical science.

[26]  M. Karamanoglu,et al.  An analysis of the relationship between central aortic and peripheral upper limb pressure waves in man. , 1993, European heart journal.

[27]  Eduardo Gil,et al.  Detection of decreases in the amplitude fluctuation of pulse photoplethysmography signal as indication of obstructive sleep apnea syndrome in children , 2008, Biomed. Signal Process. Control..

[28]  Sijung Hu,et al.  Poincaré plot analysis for pulse interval extracted from non-contact photoplethysmography , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[29]  R E De Meersman,et al.  Deriving respiration from pulse wave: a new signal-processing technique. , 1996, The American journal of physiology.

[30]  M. Nitzan,et al.  Verylow frequency variability in arterial blood pressure and blood volume pulse , 2006, Medical & Biological Engineering & Computing.

[31]  L. Nilsson,et al.  Macrocirculation is not the sole determinant of respiratory induced variations in the reflection mode photoplethysmographic signal. , 2003, Physiological measurement.