-
Notifications
You must be signed in to change notification settings - Fork 17
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Ventilation times #12
Comments
eicu.respiratoryCare contains ventEndOffset and ventStartOffset which would be very useful for this. However, their values do not make much sense: I'm checking whether that is just the way it is or whether we can get their correct values. |
The MIMIC feature we were using as a cofounder was: `tidal_high_count/total_count AS tidal_high_count2 derived from:
derived from:
Would we compute something similar from ventEndOffset and ventStartOffset? |
ventEndOffset and ventStartOffset are very useful, if their values made sense as currently whenever ventStartOffset > 0, then ventEndOffset < ventStartOffset, which is impossible according to the description in https://eicu-crd.mit.edu/eicutables/respiratorycare/. I've asked Mornin in Slack about his. If they were to make sense, we could do something like (edited from
|
Ventilation end times are probably not directly available: MIT-LCP/eicu-code#49 End times can maybe be estimated based on presence of ventilation records: MIT-LCP/eicu-website#36 |
#27 adds a MarkDown table that describes in which eICU tables what information can be found. I've tried to determine ventilation times using oxygen flow (#20 discusses oxygen flow) but that yields only a tenth of the patients as receiving supplementary oxygen for 48 hours. I'll involve more indicators of oxygen therapy in the hope to detect oxygen therapy in a larger subset of the patients. I've been doing this determining of ventilation times within R. |
Pull request #28 addresses this issue mostly. It uses the tables Also, there are still some improvements necessary to the ventilation times. Lists of text values that are interpreted as oxygen therapy are not necessarily complete or validated. Also, we'd ideally split out between categories of oxygen therapy, e.g. nasal cannula versus mechanical ventilation. I'll open an issue for the latter. |
Extract start and end times of mechanical ventilation for the eICU data.
https://github.com/MIT-LCP/mimic-code/blob/master/concepts/durations/ventilation-durations.sql does it for the MIMIC data.
The text was updated successfully, but these errors were encountered: