We all know how a disturbed night’s sleep can set us back the next day, affecting our performance and ability to work. For those with sleep disorders, this isn’t an occasional occurrence, but a continual condition that affects their health and their quality of life.
One of the most common sleep disturbance condition is obstructive sleep apnoea-hypopnea syndrome (OSAHS). This is when breathing becomes obstructed during sleep. Sufferers will have at least five episodes per hour, causing them to choke or to wake (or both). This also causes fluctuating oxygen levels and raises the risks of a stroke or cardiac problems.
OSAHS is common but not often recognised, as diagnosis of this and other sleep disorders usually involves intrusive measurement techniques such as polysomnography (PSG). Polysomnography involves the patient sleeping overnight in a lab attached to various monitoring equipment, which is intrusive, inconvenient – and expensive.
A team of members of the Institute of Electrical and Electronics Engineers (IEEE) decided to explore other ways of diagnosing the condition that would be less intrusive (1). Their solution was to fit load cells under the bed to monitor the patient’s movements, respiration and heart rate. The technique accurately distinguished between two types of breathing disorders (apnoeas and hypopnoeas) as opposed to normal breathing.
The team chose a load cell-based solution as it provided:
“A unique opportunity to continuously and unobtrusively monitor patients while they sleep. The patterns of changing force at each support can be analyzed, and inferences about various sleep parameters can be made. Load cell data can be collected continuously in a person’s home, giving physicians and researchers the ability to monitor a patient’s sleep over time without interfering with the patient or their sleep.”
Load cells had previously been used to detect patient’s movements while in bed, as well as assess sleep hygiene and to detect heart rate and respiration. The team wanted to extend this to detect “disordered breathing”, by placing a single load cell under each support leg of the bed, six in total. The data was then filtered.
“We extracted features from the raw and filtered load cell signal and used these to train a Bayesian classifier to differentiate normal and disrupted breathing.”
(For technical details of the filtering used, see the full article a cited below.)
The team saw great potential in the use of load cell technology for monitoring sleep and detecting periods of sleep apnoea, due to its simplicity of installation and application.
“The true potential of this technology for assessing sleep disorders lies in its unobtrusive nature, and on the fact that it could be used to assess disrupted sleep in a person’s own bed. Once in place, multiple nights of data may be obtained without a significant increase in cost. The potential cost savings in a tool that could be used to pre-screen for sleep apnoea, or to follow treatment, is significant. Load cells may make informative longitudinal unobtrusive monitoring of sleep a reality.”
(1) Beattie, Z. T., Hagen, C. C., Pavel, M., & Hayes, T. L. (2009). Classification of Breathing Events Using Load Cells under the Bed. Conference Proceedings, 2009, 3921–3924.