search

YerevaNN / mimic3-benchmarks

Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.
https://arxiv.org/abs/1703.07771
MIT License
805 stars 329 forks source link

Fraction of inspired oxygen is different after python3 support commit. #40

Open hrayrhar opened 6 years ago

hrayrhar commented 6 years ago

23 introduces some differences in the created datasets. The difference is present only in the Fraction of inspired oxygen columns (about 50 stays affected). All the differences have the same from: before the commit the value was 0.00x and after the commit it is 0.x.

The difference is probably caused by this change https://github.com/YerevaNN/mimic3-benchmarks/commit/d1345ff46bef8696d3a1d95d66cd57529c50a4ff#diff-1d490cd0d31a8ee697543d2ab47815e8L141. It seems that this fixes something, because 0.00x values for fraction of inspired oxygen are very strange, usually it is 0.x.

turambar commented 6 years ago

Should we close this?

hrayrhar commented 6 years ago

This is something we would like to fix in the future versions of the dataset. Right now we process fio2 of ~50 patients incorrectly.