Jesse Raffa

Data errors do happen in real data. Also, please see my response to: https://github.com/MIT-LCP/eicu-code/issues/190

Hi @EvaniLach I haven't looked into this myself, but I assume the values are summed for the reason you said, to sum over the different types of measurements. What you...

I honestly do not know. A couple of reasons this may be the case: 1) eICU-CRD ICUs tend to be slightly lower acuity and rural hospitals and may not be...

Sometimes data errors do occur. If it suits your use case, you may want to cross-reference these outcome data against APACHE-eligible patients in the `apachepatientresult` table, which has `actualhospitalmortality` and...

These tables may represent different data collection processes, so unless the values have the same offset, your observations are not necessarily inconsistent. Documentation practices may also vary between hospitals.

I'm not quite sure. Perhaps @obadawi can chime in. - `labtypeid=7` for all, so appears to be ABG related. - The handful I've looked at seem to be preceding other...

Hi, > the remainder not having any data in the same field Do you mean you can see the field and it's left blank, or you return no relevant records/rows...

Can you post the query you're using? If you would prefer to e-mail it, send it to my username at mit.edu

I'm not sure if 'ae' is significant or a typo. MAP can be found in many different places. Timestamped data is available in `vitalaperiodic` and `nursecharting`. If you are looking...

I wouldn't personally read too much into the order of the ids. Unfortunately we don't have and likely will not get this admission order information. You mention many of the...