Automatic sleep and wake classifier with heart rate and pulse oximetry: Derived dynamic time warping features and logistic model

This paper presents a novel sleep/wake classification method based on heart rate and pulse oximetry, using logistic model with derived dynamic time warping and correlation features introduced, which were used to classify sleep stages. 100 sleep recordings obtained from the Sleep Heart Health Study dataset, which are available on websites, were used to validate the proposed method. Using the features extracted by our research, classification performance of a LD classifier and feedforward neural classifier were compared to the proposed logistic classifier. The classification accuracy and AUC of the logistic classifier was found to be better (83.8%, 0.924) than those of the two other classifiers (80.1%, 0.732 for LD and 64.0%, 0.801 for neural classifier). The result demonstrated that the proposed logistic classifier using the derived dynamic time warping and correlation features extracted from heart rate and pulse oximetry signals can classify sleep stages efficiently and effectively, which can provide a novel way to carry out automatic sleep stage classification with a wearable device.

[1]  J. Carrier,et al.  Wake detection capacity of actigraphy during sleep. , 2007, Sleep.

[2]  A. Chesson,et al.  The American Academy of Sleep Medicine (AASM) Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications , 2007 .

[3]  Ricardo Vilalta,et al.  Cluster Validation , 2009, Encyclopedia of Data Warehousing and Mining.

[4]  G. Breithardt,et al.  Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. , 1996 .

[5]  A. Malliani,et al.  Heart rate variability. Standards of measurement, physiological interpretation, and clinical use , 1996 .

[6]  Urbano Nunes,et al.  Automatic sleep staging: A computer assisted approach for optimal combination of features and polysomnographic channels , 2013, Expert Syst. Appl..

[7]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[8]  Bonnie K. Lind,et al.  Methods for obtaining and analyzing unattended polysomnography data for a multicenter study. Sleep Heart Health Research Group. , 1998, Sleep.

[9]  Claudio A. Perez,et al.  Extracting Fuzzy Rules From Polysomnographic Recordings for Infant Sleep Classification , 2006, IEEE Transactions on Biomedical Engineering.

[10]  C. Heneghan,et al.  Sleep staging using cardiorespiratory signals , 2007 .

[11]  S. K. Palei,et al.  Logistic regression model for prediction of roof fall risks in bord and pillar workings in coal mines: an approach. , 2009 .

[12]  N. Douglas.  Breathing During Sleep in Normal Subjects , 1987 .

[13]  Elke Naujokat,et al.  Sleep/wake detection based on cardiorespiratory signals and actigraphy , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[14]  Eamonn J. Keogh,et al.  Derivative Dynamic Time Warping , 2001, SDM.

[15]  Xi Long,et al.  Sleep and Wake Classification With Actigraphy and Respiratory Effort Using Dynamic Warping , 2014, IEEE Journal of Biomedical and Health Informatics.

[16]  Yu-Liang Hsu,et al.  Automatic sleep stage recurrent neural classifier using energy features of EEG signals , 2013, Neurocomputing.

[17]  Zhao Hongyao.  Study of measuring heart rate and respiration rate based on PPG , 2011 .

[18]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[19]  Xi Long,et al.  On the impact of arousals on the performance of sleep and wake classification using actigraphy , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[20]  Matteo Matteucci,et al.  Sleep staging from Heart Rate Variability: time-varying spectral features and Hidden Markov Models , 2010 .

[21]  E. Wolpert.  A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. , 1969 .

[22]  Miad Faezipour,et al.  Efficient sleep stage classification based on EEG signals , 2014, IEEE Long Island Systems, Applications and Technology (LISAT) Conference 2014.

[23]  Hiroshi Tanaka,et al.  Sleep-States-Transition Model by Body Movement and Estimation of Sleep-Stage-Appearance Probabilities by Kalman Filter , 2010, IEEE Transactions on Information Technology in Biomedicine.

[24]  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.

[25]  Michael R. Neuman,et al.  Sleep Versus Wake Classification From Heart Rate Variability Using Computational Intelligence: Consideration of Rejection in Classification Models , 2008, IEEE Transactions on Biomedical Engineering.

[26]  Matteo Matteucci,et al.  Sleep Staging Based on Signals Acquired Through Bed Sensor , 2010, IEEE Transactions on Information Technology in Biomedicine.

[27]  Steffen Leonhardt,et al.  Automatic Feature Selection for Sleep/Wake Classification with Small Data Sets , 2013, BIOINFORMATICS.

[28]  Dario Floreano,et al.  Adaptive Sleep–Wake Discrimination for Wearable Devices , 2011, IEEE Transactions on Biomedical Engineering.

[29]  Dario Floreano,et al.  Sleep and Wake Classification With ECG and Respiratory Effort Signals , 2009, IEEE Transactions on Biomedical Circuits and Systems.