Submit manuscript...
eISSN: 2577-8285

Sleep Medicine and Disorders: International Journal

Editorial Volume 1 Issue 2

Long term sleep quality assessment: a new hope

Md Aktaruzzaman

Department of Computer Science and Engineering, Islamic University, Bangladesh

Correspondence: Md Aktaruzzaman, Associate Professor,Department of Computer Science and Engineering, Islamic University, Kushtia, 7003, Bangladesh

Received: October 23, 2017 | Published: October 24, 2017

Citation: Aktaruzzaman M. Long term sleep quality assessment: a new hope. Sleep Med Dis Int J. 2017;1(2):44-45. DOI: 10.15406/smdij.2017.01.00009

Download PDF


quality of sleep, sedative drugs, unconscious, dream, neurologist


NREM, non-rapid eye movement; REM, rapid eye movement; PSG, polysomnography; EEG, electroencephalogram; EOG, electro-oculogram; EMG, electro-myogram; ESS, epworth sleepiness scale; Act, actigraphy; ANS, autonomic nervous system


Physiologically sleep is defined as a state during which an individual’s brain wave activity changes and her/his nervous system is less reactive to external stimuli (i.e., temporarily unconscious). But, this temporal unconsciousness or sleeping is not constant throughout the night or bed time (the time an individual spent in bed). Actually, it cycles through five distinct stages: non-rapid eye movement stage 1 (NREM1) to NREM3, REM, and wakefulness (WAKE) according to the guidelines of American Academy of Sleep Medicine.1 It is important to note that NREM1 is the lightest sleep stage with decreased consciousness, but the brain still process some external information around the individual (e.g., during listening to a bore lecture with decreased consciousness, when listening his name or some other stimulus jolts him awake). NREM2 is the intermediate light sleep stage during which it is harder to awake an individual, and NREM3 is the deepest, the most restful and most restorative sleep stage. The next and final stage of sleep is REM (Rapid Eye Movement) sleep during which people dream; People spend more time in this stage in the late night.

Sleep is considerably recognized as an important lifestyle contributor to health, and nowadays an increasing number of populations are curtailing sleep in the name of social, leisure, or work-related activities.2 Sleep is especially considered to be important to body restitution, like thermoregulation, energy conservation, and tissue recovery,3 moreover, sleep is essential for cognitive performance, especially memory consolidation.3,4 A number of studies5–7 reported that individuals with sleep disorder (a condition that frequently effects an individual’s ability to have sufficient amount of sleep) e.g., insomnia, sleep apnea, etc are at significantly higher risks for cardiovascular diseases, cerebrovascular diseases (coronary heart disease, heart failure, stroke,…) metabolic disorder (e.g., type II diabetes mellitus, hypertension, …). In addition, a poor quality of sleep or sleepiness has been identified as one of the main reasons of car accidents.8,9 However, detection of sleep disorder or assessing poor sleep quality and subsequent treatment10,11 can significantly improve the quality of life and hence reduce mortality. Besides sleeping pills (sedative drugs), physicians can advise physical exercise, relaxation techniques and leading more disciplinary life styles12,13 for sleep disordered patients.

The precondition of providing any treatment is diagnosis and identifying if an individual is suffering from sleep disordered problem. The quality of sleep is assessed professionally in an especial sleep laboratory using whole night polysomnography (PSG), which requires signals from multiple sensors like electroencephalogram (EEG), electro-oculogram (EOG), and electro-myogram (EMG). Unfortunately, this objective (the standard) measure suffers from some unavoidable serious limitations such as the need of a sleep expert (or Neurologist), expensive equipments, an especial sleep laboratory, which make PSG unsuitable for monitoring large populations. Besides these, the normal behaviour of sleep of a person can even be affected by the new environment and wearing surface electrodes to monitor her/his brain wave. In addition, the investigations to diagnose circadian rhythm sleep disorder or to ascertain an individual’s sleep habit which requires long term (over the weeks or months long) monitoring of sleep vs wake pattern is not possible with PSG. There are both subjective e.g., Epworth Sleepiness Scale (ESS)14 and objective e.g., Actigraphy (Act)15 methods other than PSG. Although, subjective measurement methods are easy to administer, and they are less accurate than objective methods16 and there is also a chance of misperceptions of sleep state. Many earlier studies17–19 have reported sleep vs wake classification from heart rate variability i.e., the variability in the time interval between successive heart beats of an electrocardiogram signal which has the advantages of low cost and non-invasive. However, sleep staging from only HRV is still far from widespread practical implementation due to its lower accuracy.17–19

The state of autonomic nervous system (ANS) function is thought to be different between NREM and REM/WAKE stages,17,20 while it is similar between REM sleep and WAKE. Whereas, the body movement magnitudes differ between REM sleep and WAKE due to its suppressed magnitude during REM sleep. Thus, a multistage (WAKE, NREM and REM) of sleep with better accuracy is possible from the combination of HRV and ACT data. A plenty of works15,18,21,22 are available that proposed sleep staging either from HRV or wrist ACT, but to the best of my knowledge, none of them considered the combination of both data. The advantages of ACT are that they are low cost, comfortable to use, small size… etc. Mobile-health applications represent the new paradigm of tele-home care monitoring that combines the standard telemedicine approach with the latest Internet of Things concept.23 In this context, the development of a new generation of sensors led to aggregate different types of sensing units in a single device. Typical examples are wearable T-shirts with ACT and ECG sensors or smart watch with skin conductance and ACT. Inspired from the state-of-art of sleep quality assessment applications and from the recent trend of new sensors, recently, we first interested24 in sleep wake classification from the combination of HRV and chest ACT instead of wrist ACT, so that if the combination of these signals give acceptable accuracy, all sensors can be integrated on a single belt or T-shirt, which might facilitate the wearing and use of the systems by inexperienced users as well as providing long-term sleep monitoring.

The classification (binary classification) model proposed in the previous study24 was performed on a very small (only 18 subjects) data set which could have a higher risk of over fitting to the data, as a result it could result a lower performance when applied to a new unknown data from other subjects. The combination of Chest ACT with HRV performed similarly to that of Wrist ACT with HRV which at least opens the possibility of integrating all types of sensors in a single wearable device. However, instead of using the combined information of both HRV and ACT for a binary classification (Sleep vs Wake), the robust HRV features reflecting the autonomic function state can be used for separating NREM sleep from WAKE and REM sleep in the first stage, and in the second hierarchical stage, WAKE can be distinguished from the REM sleep using actigraphy features. Thus, the binary classification problem will be transformed to a ternary (NREM, REM and WAKE) classification problem with the possibility of increasing classification performance. Of course, its performance will depend on the appropriate features extraction and classifiers used in both stages. Hence, more extensive research on a large database including subjects of all categories with respect to age, sex, pathology and healthy conditions are needed to generalize the effectiveness, efficiency and appropriateness of the usage of combined information from chest actigraphy and heart rate variability. If the concept is proved effectively on a large dataset, it will allow long term sleep monitoring of an individual in home environment without the assistance of a sleep expert. Then people will not be needed to wait for an appointment with the Neurologist and will save a lot of money and time used for traditional expensive polysomnography based sleep monitoring.



Conflict of interest

The author declares no conflict of interest.


  1. Iber C, Ancoli-Israel S, Chesson AL, et al. The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications. 1st ed. Westcherster, USA: American Academy of Sleep Medicine; 2007.
  2. St-Onge MP, Grandner MA, Brown D, et al. Sleep duration and quality: impact on lifestyle behaviors and cardiometabolic health: a scientific statement from the american heart association. Circulation. 2016;134(18):e367–386.
  3. Maquet P. The role of sleep in learning and memory. Science. 2001;294(5544):1048–1052.
  4. Stickgold R, Walker MP. Sleep-dependent memory consolidation. Sleep Med. 2007;8(4):331–343.
  5. Canivet C, Nilsson PM, Lindeberg SI, et al. Insomnia increases risk for cardiovascular events in women and in men with low socioeconomic status: a longitudinal, register-based study. J Psychosom Res. 2014;76(4):292–299.
  6. Nagai M, Hoshide S, Kario K. Sleep duration as a risk factor for cardiovascular disease-a review of the recent literature. Curr Cardiol Rev. 2010;6(1):54–61.
  7. Gangwisch JE, Heymsfield SB, Boden-Albala B, et al. Sleep duration as a risk factor for diabetes incidence in a large U.S. sample. Sleep. 2007;30(12):1667–1673.
  8. Philip P, Chaufton C, Orriols L, et al. Complaints of poor sleep and risk of traffic accidents: a population-based case-control study. PLOS One. 2014;9(12):e114102.
  9. De Mello MT, Narciso FV, Tufik S, et al. Sleep disorders as a cause of motor vehicle collisions. Int J Prev Med. 2013;4(3):246–257.
  10. Chokroverty S. Diagnosis and treatment of sleep disorders caused by comorbid disease. Neurology. 2000;54(5 Suppl 1):S8–15.
  11. Abad VC, Guilleminault C. Diagnosis and treatment of sleep disorders: a brief review for clinicians. Dialogues Clin Neurosci. 2003;5(4):371–388.
  12. disorders/?gclid=CjwKCAjwmqHPBRBQEiwAOvbR8zWh2qymll1bjhiSTYJy0KYe2OOPVlvZ
  14. Vignatelli L, Plazzi G, Barbato A, et al. Italian version of the Epworth sleepiness scale: external validity. Neurol Sci. 2003;23(6):295–300.
  15. Kripke DF, Mullaney DJ, Messin S, et al. Wrist actigraphic measures of sleep and rhythms. Electroencephalogr Clin Neurophysiol. 1978;44(5):674–676.
  16. Nakazaki K, Kitamura S, Motomura Y, et al. Validity of an algorithm for determining sleep/wake states using a new actigraphy. J Physiol Anthropol. 2014;33:31.
  17. Vanoli E, Adamson PB, Ba-Lin, et al. Heart rate variability during specific sleep stages. A comparison of healthy subjects with patients after myocardial infarction. Circulation. 1995;91(7):1918–1922.
  18. Xiao M, Yan H, Song J, et al. Sleep stages classification based on heart rate variability and random forest. In Biomed Signal Process and Control. 2013;8(6):624–633.
  19. Aktaruzzaman M, Migliorini M, Tenhunen M, et al. The addition of entropy-based regularity parameters improves sleep stage classification based on heart rate variability. Med Biol Eng Comput. 2015;53(5):415–425.
  20. Elsenbruch S, Harnish MJ, Orr WC. Heart rate variability during waking and sleep in healthy males and females. Sleep. 1999;22(8):1067–1071.
  21. Van Hees VT, Sabia S, Anderson KN, et al. A novel, open access method to assess sleep duration using a wrist-worn accelerometer. PLoS One. 2015;10(11):e0142533.
  22. Mourad A, Jiang Z, Zhonghong Y. Sleep-wake stages classification and sleep efficiency estimation using single-lead electrocardiogram. Expert Syst Appl. 2012;39(1):1401–1413.
  23. Silva BM, Rodrigues JJ, de la Torre Díez I, et al. Mobile-health: A review of current state in 2015. J Biomed Inform. 2015;56:265–272.
  24. Aktaruzzaman M, Rivolta MW, Karmacharya R, et al. Performance comparison between wrist and chest actigraphy in combination with heart rate variability for sleep classification. Comput Biol Med. 2017;89:212–221.
Creative Commons Attribution License

©2017 Aktaruzzaman. This is an open access article distributed under the terms of the, which permits unrestricted use, distribution, and build upon your work non-commercially.