Automatic sleep staging is a beneficial tool in the field of sleep since it reduces the tedious visual analysis required by long duration EEG recordings. During the last 20 years, although a number of automated systems have been developed for routine sleep staging, none have met the reliability criteria required by sleep clinicians. Almost all of these systems are rule-based expert systems and errors occurred when emulating a sleep expert's subjective judgement. In the last three years, several studies have shown a significant increase in reliability using alternate analysis methods, particularly those better suited to emulate human thought processing. The goal of this project is to develop low cost automated sleep staging software for sleep laboratories and portable screening/monitoring devices that shows a significant increase in somnologist/computer agreement for a large validation study. the project will address wide patient age groups and algorithm adaptation to individual somnologist. The algorithms will implement the criteria described in Rechtschaffen and Kales' manual for sleep staging using a combination of neural network and fuzzy logic signal processing technology.
A large customer base exists and is growing with the advent of home monitoring. With a successful large validation study this product will be the first automated sleep staging software to be accepted by the sleep community. Reliability, low cost, and accessibility for any lab with a MS-Windows or Macintosh system will be the selling points of this software.
