You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for making all this code public! I was looking through the ETL flow and there is one thing I do not quite understand: In the PhysioNet documentation of the MIMIC IV data v2.2, it states that "the anchor_age provides the patient age in the given anchor_year". Hence, it would seem the patient's year of birth (in shifted MIMIC time) should be anchor_year - anchor_age. However, looking at this line of the conversion code (from etl/etl
/cdm_person.sql), it seems the CDM year of birth is set directly to the anchor year (the anchor age is only used in etl/lk_procedure.sql in a different context, as far as I can tell). Did I misunderstand smt. or miss a part of the puzzle?
The text was updated successfully, but these errors were encountered:
Thanks for making all this code public! I was looking through the ETL flow and there is one thing I do not quite understand: In the PhysioNet documentation of the MIMIC IV data v2.2, it states that "the anchor_age provides the patient age in the given anchor_year". Hence, it would seem the patient's year of birth (in shifted MIMIC time) should be
anchor_year - anchor_age
. However, looking at this line of the conversion code (from etl/etl/cdm_person.sql), it seems the CDM year of birth is set directly to the anchor year (the anchor age is only used in etl/lk_procedure.sql in a different context, as far as I can tell). Did I misunderstand smt. or miss a part of the puzzle?
The text was updated successfully, but these errors were encountered: