We use cookies and other tools to enhance your experience on our website and to analyze our web traffic.
For more information about these cookies and the data collected, please refer to our Privacy Policy.

Sleep apnea scoring in STAGES dataset

7 posts
Was this reply useful? Learn more...
 
[-]
CC +0 points · 11 months ago

Hi NSRR team:

Thank you for your every great contribution!

I would like to use STAGES dataset, especially sleep-disordered breathing labels, which are recorded as .csv files (for example, stages/files/original/STAGES PSGs/ MSMI/MSMI00001.csv).

My question is whether those .csv files were scored by sleep experts or the results from the automatic scoring algorithm.

I also tried to find some information about it, but I couldn't find any clear description.

Can you help me with this issue?

Thank you

442 posts
bio
Was this reply useful? Learn more...
 
[-]
mrueschman +0 points · 11 months ago

Hey CC - thanks for checking out the site. I agree this could be made clearer in the STAGES documentation.

Another user asked about this on the Forum last year; I provided the details I could find about the manual sleep scoring: https://sleepdata.org/forum/stages-ground-truth-hypnogram/

In short: Yes, the STAGES PSG data were scored by sleep experts.

7 posts
Was this reply useful? Learn more...
 
[-]
CC +0 points · 11 months ago

Thank you for your response. I understand that sleep staging is annotated by experts, and I would like to further confirm whether the annotation of sleep apnea events has also been conducted and validated by domain experts. Additionally, I would like to inquire if the Apnea-Hypopnea Index (AHI) in the dataset ( https://sleepdata.org/datasets/stages/files/m/browser/original/De-identified%20Data/PSG%20SRBD%20Variables/STAGESPSGKeySRBDVariables2020-08-29%20Deidentified.xlsx ) is derived from the annotation of respiratory events. I noticed that there is information about the scoring of sleep breathing events in page 27 of the document ( https://sleepdata.org/datasets/stages/files/m/browser/original/STAGES%20SOPs/30K%20PSG%20Operational%20Plan%202017-03-31.pdf?inline=1 ), indicating that the annotations were done by an algorithm developed by the team. Therefore, I have some confusion.

442 posts
bio
Was this reply useful? Learn more...
 
[-]
mrueschman +0 points · 11 months ago

I received confirmation of the following from the STAGES data contributor:

  1. All the PSG annotations (staging, respiratory events) came from human scoring (sleep labs at each clinical site)
  2. The "SRBDVariables" spreadsheet was derived from the PSG annotation files.

I think the references in that supplemental documentation were discussing the possibility of using automated algorithms to further analyze the STAGES PSG data.

7 posts
Was this reply useful? Learn more...
 
[-]
CC +0 points · 11 months ago

Thank you!