Summary:
Sleep is a complex process that plays a key role in maintaining homeostasis, well-being and overall health. Even though, humans should spend up to one-third of their life sleeping, the current 24-hour society is keeping them from getting the necessary amount of sleep. This, so- called, “sleep deprivation” has been associated with reductions of cognitive and behavioural performance, depression, memory loss, and cardiovascular diseases. This reduction in sleep quality is, however, not only caused by the high demands of society, but also by sleep disorders, such as insomnia and sleep apnea.
The gold standard in sleep medicine is the polysomnography (PSG), which is a sleep test used to monitor sleep and diagnose sleep disorders. Although PSG is the most powerful tool in sleep medicine, it requires overnight hospitalization and it is associated with high costs and reduced comfort. The reason for this relies on the fact that PSG requires, on the one hand, costly sleep centre facilities and sleep experts, and on the other hand, the use of instruments that may interfere with the normal sleep pattern. These limitations have motivated a numerous amount of studies, where the focus has been on the development of non-intrusive technologies for the monitoring of sleep. These new technologies aim to bring sleep monitoring to a home environment, where the assessment of sleep quality can be done during more than one night. In addition, these technologies might improve the continuous monitoring of sleep in infants, since sleep is also one of the most important factors in their neural development, particularly for preterm infants. Therefore, continuous sleep monitoring could provide an indicator of such development over time. Moreover, non-intrusive sleep monitoring methods are required to ensure a comfortable measurement, with a minimal burden on infants.
In this context, this workshop summarizes different technologies and algorithms that have been developed for the monitoring of sleep in preterm infants and adults using non-intrusive sensors.
The first talk will focus on the development of a ballistocardiographic system that can be used to monitor sleep in preterm infants. Then, algorithms for sleep/wake detection using actigraphy for insomniacs will be introduced. After that, a method based on the oxygen saturation (SpO2) signal, used for predicting cardiac comorbidity of patients suffering from obstructive sleep apnea (OSA) will be discussed. Next, a summary of algorithms based on pulse photoplethysmography used to detect OSA will be presented, and finally, research on the use of the ECG-derived respiratory signal for sleep monitoring will be summarized.
Presentations
- Rohan Joshi (TU/e)
A ballistocardiographic setup for monitoring movement in preterm infants - Xi Long (Philips Research)
Sleep/Wake detection for insomniacs - Margot Deviaene (KU Leuven)
Cardiac phenotyping of OSAS patients using oxygen saturation - Jesus Lazaro (KU Leuven)
Towards a detection of obstructive sleep apnea syndrome based on pulse - Carolina Varon (KU Leuven)
The use of the ECG-derived respiration in the detection of sleep apnea
Organizer Information
Names/emails: Carolina Varon carolina.varon@esat.kuleuven.be Xi Long xi.long@philips.com
Short Biography of Organizers
Dr. Ir. Carolina Varon received the B.Sc. degree in electronic engineering from the Universidad de Ibagué, Ibagué, Colombia, in 2005. From 2002 to 2003, she was a Site Engineer in Agroindustrial del Tolima, Ibagué, Colombia, and in 2005 she joined Security Solutions, Bogotá, Colombia, where she was the Technical Support for Latin America until 2007. In 2007 she moved to Leuven, Belgium, where two years later she received the M.Sc. degree in astronomy and astrophysics and in 2010 the M.Sc. degree magna cum laude in artificial intelligence, both from the Katholieke Universiteit Leuven. In 2011 she joined STADIUS, Department of Electical Engineering (ESAT), KU Leuven as a PhD student, where she worked in close collaboration with the sleep laboratory and the epilepsy clinic, both of the University hospital Leuven (UZ Leuven). In 2015 she defended her PhD dissertation entitled “Mining the ECG: Algorithms and Applications”.
She is currently a postdoctoral researcher of the Research Foundation Flanders (FWO) and her current research interests include the development of signal processing and machine learning techniques for the analysis of cardiorespiratory interactions in sleep apnea and epilepsy.
Dr. Ir. Xi Long was born in Ganzhou, China, in 1983. He received the B.Eng. degree in electronic information engineering from Zhejiang University, Hangzhou, China, in 2006, and the M.Sc. and the Ph.D. degree (cum laude) in electrical engineering from the Eindhoven University of Technology (TU/e), Eindhoven, the Netherlands, in 2009 and 2015, respectively.
He is currently a scientist at Philips Research and an assistant professor at TU/e, Eindhoven, the Netherlands. His research interests include unobtrusive and wearable sensing, biomedical signal processing and machine learning in healthcare.