Coder Social home page Coder Social logo

lanyexiaosa / multitask-patients Goto Github PK

View Code? Open in Web Editor NEW

This project forked from mit-caml/multitask-patients

0.0 1.0 0.0 15 KB

The code for the models described in "Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU" (KDD 2018).

Python 100.00%

multitask-patients's Introduction

Learning Tasks for Multitask Learning

The code in this repository implements the models described in the paper Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU (KDD 2018). There are two files:

  1. generate_clusters.py, which trains a sequence-to-sequence autoencoder on patient timeseries data to produce a dense representation, and then fits a Gaussian Mixture Model to the samples in this new space.

  2. run_mortality_prediction.py, which contains methods to preprocess data, as well as train and run a predictive model to predict in-hospital mortality after a certain point, given patients' physiological timeseries data.

For more information on the arguments required to run each of these files, use the --help flag.

Data

Without any modification, this code assumes that you have the following files in a 'data/' folder:

  1. X.h5: an hdf file containing one row per patient per hour. Each row should include the columns {'subject_id', 'icustay_id', 'hours_in', 'hadm_id'} along with any additional features.
  2. static.csv: a CSV file containing one row per patient. Should include {'subject_id', 'hadm_id', 'icustay_id', 'gender', 'age', 'ethnicity', 'first_careunit'}.
  3. saps.csv: a CSV file containing one row per patient. Should include {'subject_id', 'hadm_id', 'icustay_id', 'sapsii'}. This data is found in the saps table in MIMIC III.
  4. code_status.csv: a CSV file containing one row per patient. Should include {'subject_id', 'hadm_id', 'icustay_id', 'timecmo_chart', 'timecmo_nursingnote'}. This data is found in the code_status table of MIMIC III.

multitask-patients's People

Contributors

harinisuresh avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.