shaoxiong 22d37e4cb6 | 3 years ago | |
---|---|---|
.gitignore | 3 years ago | |
GatedCNN.py | 3 years ago | |
LICENSE | 3 years ago | |
README.md | 3 years ago | |
dataloader.py | 3 years ago | |
embeddings.py | 3 years ago | |
layers.py | 3 years ago | |
main.py | 3 years ago | |
models.py | 3 years ago | |
optimizations.py | 3 years ago | |
options.py | 3 years ago | |
train_test.py | 3 years ago | |
utils.py | 3 years ago |
Sign the data use agreement and download MIMIC-III dataset from PhysioNet.
Organize your data using the following structure
data
| D_ICD_DIAGNOSES.csv
| D_ICD_PROCEDURES.csv
| ICD9_descriptions
└───mimic3/
| | NOTEEVENTS.csv
| | DIAGNOSES_ICD.csv
| | PROCEDURES_ICD.csv
| | *_hadm_ids.csv
ICD9_descriptions
is available here, and
*_hadm_ids.csv
are available here.
MIMIC_RAW_DSUMS
is available here, while the rest file for MIMIC2 can be generated with their code.
If you use Python3 consctruct_datasest.py
in ICD9_Coding_of_Discharge_Summaries
to create data files, remember to convert dict object to list (line 82&83) and use dict.items()
instead of dict.iteritems()
.
Assign the directories of MIMIC data using MIMIC_3_DIR
.
python3 main.py
Configs available at options.py
.
Requirements:
The code is based on the following two great repositories.