Implementation for Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning

Usage

https://github.com/tanlab/ConvolutionMedicalNer.git
cd ConvolutionMedicalNer

Run MIMIC-Extract Pipeline as explained in https://github.com/MLforHealth/MIMIC_Extract.
Copy the output file of MIMIC-Extract Pipeline named all_hourly_data.h5 to data folder.
Run 01-Extract-Timseries-Features.ipnyb to extract first 24 hours timeseries features from MIMIC-Extract raw data.
Copy the ADMISSIONS.csv, NOTEEVENTS.csv, ICUSTAYS.csv files into data folder.
Run 02-Select-SubClinicalNotes.ipynb to select subnotes based on criteria from all MIMIC-III Notes.
Run 03-Prprocess-Clinical-Notes.ipnyb to prepocessing notes.
Run 04-Apply-med7-on-Clinical-Notes.ipynb to extract medical entities.
Download pretrained embeddings into embeddings folder via link in given References section.
Run 05-Represent-Entities-With-Different-Embeddings.ipynb to convert medical entities into word representations.
Run 06-Create-Timeseries-Data.ipynb to prepare the timeseries data to fed through GRU / LSTM.

12.Run 07-Timeseries-Baseline.ipynb to run timeseries baseline model to predict 4 different clinical tasks.

12.Run 08-Multimodal-Baseline.ipynb to run multimodal baseline to predict 4 different clinical tasks.

12.Run 09-Proposed-Model.ipynb to run proposed model to predict 4 different clinical tasks.

Download the MIMIC-III dataset via https://mimic.physionet.org/

Download Pre-trained Word2Vec & FastText embeddings: https://github.com/kexinhuang12345/clinicalBERT

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
data		data
embeddings		embeddings
results		results
01-Extract-Timeseries-Features.ipynb		01-Extract-Timeseries-Features.ipynb
02-Select-SubClinicalNotes.ipynb		02-Select-SubClinicalNotes.ipynb
03-Preprocess-Clinical-Notes.ipynb		03-Preprocess-Clinical-Notes.ipynb
04-Apply-med7-on-Clinical-Notes.ipynb		04-Apply-med7-on-Clinical-Notes.ipynb
05-Represent-Entities-With-Different-Embeddings.ipynb		05-Represent-Entities-With-Different-Embeddings.ipynb
06-Create-Timeseries-Data.ipynb		06-Create-Timeseries-Data.ipynb
07-TimeseriesBaseline.ipynb		07-TimeseriesBaseline.ipynb
08-Multimodal-Baseline.ipynb		08-Multimodal-Baseline.ipynb
09-Proposed-Model.ipynb		09-Proposed-Model.ipynb
README.md		README.md
preprocess.py		preprocess.py