MIMIC Benchmark in PyTorch.
Project description
MIMIC Benchmark in PyTorch
MIMIC Benchmark reimplemented in PyTorch. For examples and documentation checkout: https://torchmimic.readthedocs.io/en/latest/
Installation
To install, run:
pip install torchmimic
Data
This library contains PyTorch datasets that will load your existing MIMIC Benchmark data. To use those datasets, just import the data you want from torchmimic.data
:
from torchmimic.data import DecompensationDataset
from torchmimic.data import IHMDataset
from torchmimic.data import LOSDataset
from torchmimic.data import PhenotypingDataset
from torchmimic.data import MultitaskDataset
Models
We've included some of the models used in the benchmark paper for reproduction and comparison with your own methods. Current models include:
- Standard LSTM
You can access these models from torchmimic.models
:
from torchmimic.models import StandardLSTM
Benchmarks
Each of the benchmarks can be found in torchmimic.benchmarks
:
from torchmimic.benchmarks import DecompensationBenchmark
from torchmimic.benchmarks import IHMBenchmark
from torchmimic.benchmarks import LOSBenchmark
from torchmimic.benchmarks import PhenotypingBenchmark
from torchmimic.benchmarks import MultitaskBenchmark
At a minimum, the benchmark need a model to be trained. You can create the model from one of our existing ones or you can create your own.
Weights and Biases Support
This library has built-in logging of model configurations and key metrics using the Weights and Biases library.
TODOs
Benchmarks
- Phenotyping
- Length of Stay
- Decompensation
- In Hospital Mortality
- Multitask
Models
- Standard LSTM
- Standard LSTM + Deep Supervision
- Logistic Regression
- Channelwise LSTM
- Channelwise LSTM + Deep Supervision
- Multitask LSTM
- Multitask Channelwise LSTM
Testing
- Test data for GitHub Workflow
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for torchmimic-0.0.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | a32cab7aead19e21b55635c3dd804a430f87cfb6a5feba826b6da65ac6f9ba29 |
|
MD5 | bc6eae2693058283a8e4fa4c2f6eb462 |
|
BLAKE2b-256 | 5fb10ae5c47c6141a2c5e979dfb7bc6ba4f59e1e9fa32b6245ffe3d0f5dc8d6e |