search

alistairewj / pao2-fio2-prediction

Predict the PaO2/FiO2 ratio from non-laboratory derived data
3 stars 1 forks source link

offset updated #5

Open theonesp opened 6 years ago

theonesp commented 6 years ago

I had to update the filter since there are now start and end offset in vent_unpivot_rc https://github.com/alistairewj/pao2-fio2-prediction/blob/da0c81a44409d074e452e80343e2d5f93d62e3ae/sql/data.sql#L55 @alistairewj what do you think?

theonesp commented 6 years ago

Actually I changed it to pf.pfoffset = vent.chartoffset

alistairewj commented 6 years ago

It's not clear what information you are trying to bring in from the vent_unpivot_rc table. If you want to get yes/no ventilated, then use ventdurations. Is that the goal?

tompollard commented 6 years ago

the ventilation code is duplicated in https://github.com/MIT-LCP/eicu-northwell so we should come up with a plan for keeping them in sync (e.g. merging then deleting one, creating a new repo for this task, etc).

alistairewj commented 6 years ago

Yeah this repo is just using tables generated in that eicu-northwell repo. I'm 99% sure I centralized defining ventilation into the eicu-northwell repo and the stuff in this is just extensions e.g. give me values from eicu-northwell tables between hours 2-3, etc.