man sleeping with smartwatch

Design of Monitoring Systems for Chronic Sleep/Brain Disorders

Chronic sleep disorders such as obstructive sleep apnea (OSA) is a significant health condition, which is time consuming and expensive to diagnose. This project aims to design and clinically validate a simple monitoring systems for chronic sleep disorders.

Background

Chronic sleep disorders cause significant personal, familiar, health and societal consequences [1-3]. This is particularly true for obstructive sleep apnea (OSA) which affects more than 4% of the population [4]. Current diagnoses are based on submission primarily from the general practice when a suspicion of OSA is raised. The patients are submitted for further investigation with cardiorespiratory measures (CRM) or gold standard polysomnography (PSG), which includes measures of sleep pattern and cardio-respiratory measures [5]. The procedures are highly standardized but include diagnoses on hospital using advanced medical equipment. The recording is typically made in hospital settings (in-hospital or as ambulatory measures) but the patient need contacts with the hospital for the nocturnal stay or as home recording bringing the equipment to the hospital after the recording. The analysis is time consuming taking up to 4-5 hour analyze time for experienced technicians. Consequently, the procedure is expensive. A significant problem is that more than 50% of those submitted do not suffer from OSA. There is a need for methods for identification of patients in primary sector and/or in patients with high risk of OSA, and procedures which may screen for identification of candidates submitted for further management in hospital settings for increasing the number of positive diagnosed patients and reducing the number of patients with negative test.

Project objectives

The main objective for this research project is to design monitoring systems, for chronic sleep disorders capable of monitoring, analysis, and interpretation of abnormal events opening for ground breaking earlier and better disease treatment and prevention of serious worsening of chronic diseases and furthermore disease prevention. Intelligent multi-modal biomedical signal processing, signal interpretation, and machine learning algorithms will be designed, implemented, and clinical tested and validated using large scale clinical samples to achieve these goals.

References

  1. Jennum, P., et al. (2012) Health, social, and economic consequences of narcolepsy: a controlled national study evaluating the societal effect on patients and their partners. Sleep Med, 13, 1086-93.
  2. Jennum, P., et al. (2014) Social consequences of sleep disordered breathing on patients and their partners: a controlled national study. Eur Respir J, 43, 134-44.
  3. Jennum, P., et al. (2011) Health, social and economical consequences of sleep-disordered breathing: a controlled national study. Thorax, 66, 560-6.
  4. Jennum, P., et al. (2009) Epidemiology of sleep apnoea/hypopnoea syndrome and sleep-disordered breathing. Eur Respir J, 33, 907-14.
  5. R. Berry, R. Brooks, C. Gamaldo and et. al (2014). The AASM Manual for the Scoring of Sleep and Associated Events: Rules, terminology and Technical Specifications, American Academy of Sleep Science, 2014.

Contact

Mads Olsen
PhD student
DTU Electrical Engineering

Contact

Helge Bjarup Dissing Sørensen
Associate Professor MSK, PhD
DTU Electrical Engineering
+45 45 25 52 44

Contact

Poul Jørgen Jennum
Professor
Rigshospitalet, Glostrup
http://www.cachet.dk/research/phd-projects/monitoring-systems
17 DECEMBER 2018