Treatment endtime is not avaliable?

[peiyaoli]

It seems that endtime of treatment is not available here? So how could we find the treatment duration? Such as duration of CRRT? @tompollard @alistairewj

[alistairewj]

It's not trivial - we haven't identified a method yet but I imagine it would be similar to MIMIC - examining the data, looking to see if there are trends in the documentation (e.g. it occurs every 12 hours), then defining a rule for endtime (e.g. no documentation after 16 hours).

[rincont]

I agree that this is not trivial - different treatments would require different end times. For example CRRT calculations may be required as frequently as 100 to 160 times in a 24 hour period and nurse are documenting hourly so an end time of 16 hours without documentation is not meaningful.

[peiyaoli]

Could you please to give us a demo? @alistairewj

[alistairewj]

Not sure I'll have time to look at this in the next few weeks. @tompollard will be releasing an intake output table soon and that might have some data elements to look at. Also we should probably move this discussion to eicu-code as it's not about documentation of the database.

…

On Nov 11, 2017 9:39 AM, "peiyaoli" ***@***.***> wrote: Could you please to give us a demo? @alistairewj <https://github.com/alistairewj> — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#36 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABOSdLT6VGovQdxW2tm-wl4AlyO4oIg-ks5s1bGsgaJpZM4P9d4n> .