luchang-cs / chet

Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

Context-Aware-Healthcare

Codes for AAAI 2022 paper: Context-aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs

Download the MIMIC-III and MIMIC-IV datasets

Go to https://mimic.physionet.org/ for access. Once you have the authority for the dataset, download the dataset and extract the csv files to data/mimic3/raw/ and data/mimic4/raw/ in this project.

Preprocess

python run_preprocess.py

Train model

python train.py

Configuration

Please see train.py for detailed configurations.

chet's Issues

Some problems in MIMIC-IV

Hello, I am very interested in your paper. When I used your source code to reproduce the experiment following the settings in the paper, the recall rate of the diagnostic prediction task on the MIMIC-IV dataset was very high, and the F1 evaluation index for the heart failure task was almost 0. But the same code works fine on the MIMIC-III dataset. May I ask how to adjust the code? In addition, with the hyperparameter settings you mentioned in the paper, the amount of parameters on the MIMIC-IV dataset is also somewhat different, May I ask the correct hyperparameter settings?

Version of the MIMIC datasets used in the paper

Hello, I am very interested in your paper. May I ask which version of MIMIC-III and MIMIC-IV are respectively in the paper?

Code setting problem

Hello, I am a master's student.Your work has inspired me a lot, and I am very willing to reference and compare your work. I want to know whether using the default code can achieve the best results, or need to modify some settings.Thank you verymuch.

Is the ‘icd10-icd9.csv’ in the MIMIC dataset?

Class 'Mimic4Parser' in 'preprocess/parse_csv.py' needs to load 'icd10-icd9.csv', but the csv file does not provide in mimic-4 dataset

The R@K

Hello, I am very interested in your paper. May I ask which version of MIMIC-III and MIMIC-IV are respectively in the paper?