Closed rplambec closed 6 years ago
We don't have one at the moment but if you highlight which columns have codes you are interested in we can ask the right people and add it to the documentation.
Thanks for your reply. Here are some of the columns I have questions on:
The table "id" columns are just used to ensure uniqueness of rows. They have no meaning. You'll find diagnosisid is unique to every row. I'll get back to you on the others.
You can generate the mapping for admitsource
values by linking the apachepredvar
table to the patient
table:
select distinct a.admitsource, p.unitadmitsource
from `physionet-data.eicu_crd_demo.apachepredvar` a
left join `physionet-data.eicu_crd_demo.patient` p
on a.patientunitstayid = p.patientunitstayid
order by admitsource;
Row admitsource unitadmitsource
1 -1
2 1 Operating Room
3 2 Recovery Room
4 4 Floor
5 4 Step-Down Unit (SDU)
6 4 ICU to SDU
7 5 Other ICU
8 6 Other Hospital
9 7 Direct Admit
10 8 Emergency Department
I also have the same question on what are the numbers contained in "admitsource" under ApachePredVar represents. These are so important that can change the model completely. Thanks in advance.
And it seems to me that the number of patients in each group mapped to the patient table does not make much sense, esp. there is no.3 in admitsource that is not correlated to any group. in unitadmitsource.
Is there a code manual for the eICU database, i.e. something that let's me know what the numeric codes you use in your data mean when they represent something else? For instance, when pulling up the apachePredVar table there is a row titled admitsource which can be numbered 1-8 but I am unsure what each of these different numbers represent. There are other similar rows such as amilocation, discharge location, etc. Is there a code manual that defines what these numbers represent? Thanks.