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

Question about metric alignment #141

Closed yzhHoward closed 10 months ago

yzhHoward commented 1 year ago

Thanks for your great work! I find that there are different metrics (valueom) for one lab test, such as there are F and C for temperature, oz/kg/lbs for weight. Do you align them while preprocessing these data?

hrayrhar commented 10 months ago

Yes, we do standardize such features. For example, here is the code for weight.