Way to check sleep stage
Hi Kisoong, It isn't clear to me what your question is. Annotations are available and we have some tools for accessing annotations. Let me know if you need more information.
I want know about more information.
I get the 1ch eeg raw data from openeeg device.
I just want to know is it possible check sleep stage using 1ch raw data?
It's possible to do sleep/awake from single EEG ch not full sleep staging:
Hi Farhad, Are there any published/opensource methods that you believe do a good job of sleep-wake detection?
Hi Dennis, As far as I know there is no open source method
Did you heard about MyZeo device? They also used 1ch eeg signal.
I thought they can check full sleep stage as well. but MyZeo company is gone so i can not ask about it..
I'm digging check sleep stage using 1ch eeg, but i counln't find yet
if have good reference about it just let me know
Kisoong, I found this:
Automatic Stage Scoring of Single-Channel Sleep EEG by Using Multiscale Entropy and Autoregressive Models.
I invented, published and made open source a single EEG channel sleep/wake metric. It is called z-ratio. It has been peer reviewed and published in SLEEP, and as well the AASM has kept in the loop of possible new methods for future sleep/wake automation.
IT DOES NOT STAGE SLEEP, it provides a METRIC to gauge the relative contribution of slow to fast EEG within a single channel of EEG initially in 2 seond epochs, now down to 1 second epochs. First published in 1990.
The bibliography compilation of publications can be found here: www.z-eeg.com
My presentation in Germany at Founding Congress of World Sleep Association in 2005
Same in flash. www.sleep-wake.com/zomnography.swf
The foundational basis was also recently corroborated by a study out of Boston's Mass General: http://journals.plos.org/ploscompbiol/article/asset?id=10.1371/journal.pcbi.1003866.PDF
Feel free to let me know how I can help.
ADMINS: I have applied for download rights, but have not heard back. What else do I need to do to be able to download the EDFs and start using them to investigate z-ratio on this open source of cases?
By the way, Teuniz has included z-ratio in his Open Sourced EDF browser http://www.teuniz.net/edfbrowser/
hi please can anyone help about finding a database of ECG signals to detect drowsiness phase
is it possible to find such data?
At the cost of sounding a bit naive, may I ask if there is any way to distinguish between the obstructive vs central vs other types of sleep apnea in the database. or is it given in the annotation. Many thanks for your time.
Yes, there are ways to distinguish between obstructive apneas, central apneas, and other types of events (hypopneas, desaturations, arousals, etc.) If you are looking at the annotation level, the XML files will have these different types of events marked in the "Name" field. Here's an example from one of our CHAT study XML annotation files:
If you are looking in the summary dataset (CSV) files, then there will be many indices and event counts broken down by central, obstructive, and other event categories.
Please let us know if you have additional questions, thanks!
Thank you sir,
I understand these events are all manually inspected / identified and scored in the dataset.
Guess, one would like to automate it. Any comments / leads / guidance to that or even related work are welcome.
I believe you identified what I believe could be a linch pin for unlocking the power of the data stored on the site. The scored data including apneic events provides a valuable resource for which to conduct research now by alleviating the high cost of manual scoring. With that said, being able to systematically extract common events systematically and objectively could open up sleep medicine. I believe the development of sleep event extraction could mirror what has been done with ECG R wave detection; where open source software with a range of approaches can be downloaded. I would argue that an open source sleep feature extraction toolkit would establish the framework for new measures to be explored.
I have some suggestions on how to approach. Many aspects of feature detection in sleep medicine look for a decrease in signal with a minimum duration that correspond with a value/change of another signal. A method that could be applied in multiple situations could be powerful. I don't believe the specific method is that importants. For example, ECG R wave detection approaches use wavelets, state space modeling, point processing modeling and dynamical systems approaches. Demonstrating an approach is robust to artifacts in a large data sets (plug for the NSRR dataset) would be more important than the methods (as long as it wasn't to slow).
Take a look at the open challenge problems for an example that demonstrates the challenges that arise when extracting features from PSG data.