search

lrsoenksen / HAIM

This repository contains the code to replicate the data processing, modeling and reporting of our Holistic AI in Medicine (HAIM) Publication in Nature Machine Intelligence (Soenksen LR, Ma Y, Zeng C et al. 2022).
Apache License 2.0
104 stars 27 forks source link

Definitions of records #10

Closed ArbelHaiman closed 1 year ago

ArbelHaiman commented 1 year ago

Hi,

I'm trying to create the dataset you created for the research. At MIMIC-CXR there are only the subject_id and study_id identifiers, but in MIMIC-IV, there are the subject_id, hadm_id adn stay_id. What is the correct way to link images from MIMIC-CXR to data from MIMIC-IV? I understand from your article that records are defined by {subject_id, hadm_id, stay_id}, but I don't understand how should I select the matched images to each records? Perhaps you can describe in detail what a single record is composed of, in terms of data from all sources? Thank you

AliRasekh commented 1 year ago

Hi,

This is my question as well.

lrsoenksen commented 1 year ago

We show how we assigned HAIM_IDs in the '1_1-Create Pickle Files.py file' 1_1-Create Pickle Files.py

SEE THE FOLLOWING LINE:

Get Unique Subject/HospAdmission/Stay Combinations with Chest Xrays

df_haim_ids = df_ids[df_ids['subject_id'].isin(df_cxr_ids['subject_id'].unique())]