Alistair Johnson

@jraffa maybe you have some insight into how to classify an ICU stay vs. a non-ICU stay

This is non-trivial and we welcome collaborative effort on this task!

Hm, perhaps the Foley was taken out during then? If the patient continues to have heart rate measurements during that time, then that's the most likely answer. It could be...

It might be they are in a step down ward where documentation continues. The eICU system ingests data from a lot of different systems, so sometimes you see out of...

I forgot to close this - but this was fixed in MIMIC-IV v2.0. > Fixed an issue where hospitalizations were missing edregtime and edouttime when the patient was admitted via...

I think including a date is too much and will become obsolete soon. I would suggest the following: > The creation of the deidentified database was approved by the Massachusetts...

isn't this better for the lcp wiki? that way it's not awkwardly hiding IPs and what not?

More than likely these patients are admitted before data collection for MIMIC-IV-ED starts. MIMIC-IV-ED does not include patients admitted between 2008 - 2010. You can check by joining to the...

First, since `dod` is a date, you do have to be careful of apparent "negative" survival which occurs due to subtracting a date from a datetime, e.g. for `subject_id` 19936081...

It's not strictly an error but it may result in an inconsistent data load (I haven't checked). Essentially the load uses pandas as a convenience. pandas tries a low memory...