Metadata-Version: 2.1
Name: deepsurvk
Version: 0.2.2
Summary: Implementation of DeepSurv using Keras
Home-page: https://github.com/arturomoncadatorres/deepsurvk
Author: Arturo Moncada-Torres
Author-email: arturomoncadatorres@gmail.com
License: MIT license
Keywords: deepsurvk
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Healthcare Industry
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Requires-Dist: tensorflow (>=2.2.0)
Requires-Dist: numpy (==1.18.0)
Requires-Dist: scipy (==1.4.1)
Requires-Dist: scikit-learn (>=0.21.2)
Requires-Dist: pydot (>=1.4.1)
Requires-Dist: graphviz (>=0.14.1)
Requires-Dist: lifelines (>=0.24.15)
Requires-Dist: seaborn (>=0.10.1)
Requires-Dist: pygments (>=2.5.1)
Requires-Dist: h5py (>=2.10.0)

<p align="center">
  <img src="https://github.com/arturomoncadatorres/deepsurvk/blob/master/docs/artwork/logo.png?raw=true" width="500" />
</p>

<h3 align=center> Implementation of DeepSurv using Keras</h3>

<h3 align="center">

[![PyPI version](https://badge.fury.io/py/deepsurvk.svg)](https://badge.fury.io/py/deepsurvk)
[![Build Status](https://img.shields.io/travis/arturomoncadatorres/deepsurvk.svg?branch=master)](https://travis-ci.org/arturomoncadatorres/deepsurvk)
[![Documentation](https://readthedocs.org/projects/deepsurvk/badge/?version=latest)](https://deepsurvk.readthedocs.io/en/latest/?badge=latest)
[![PyUp](https://pyup.io/repos/github/arturomoncadatorres/deepsurvk/shield.svg)](https://pyup.io/repos/github/arturomoncadatorres/deepsurvk/)

</h3>

<p align="center">
  <a href="#pray-motivation">Motivation</a> •
  <a href="#tada-features">Features</a> •
  <a href="#bookmark_tabs-documentation">Documentation</a> •
  <a href="#page_with_curl-license">License</a> •
  <a href="#black_nib-references">References</a> •
  <a href="#label-credits">Credits</a>
</p>

---
## :pray: Motivation

DeepSurv is a Cox Proportional Hazards deep neural network used for modeling interactions between a patient's covariates and treatment effectiveness. It was originally proposed by [Katzman et. al (2018)](https://bmcmedresmethodol.biomedcentral.com/articles/10.1186/s12874-018-0482-1) and [implemented in Theano (using Lasagne)](https://github.com/jaredleekatzman/DeepSurv).

Unfortunately, [Theano is no longer supported](https://groups.google.com/forum/#!msg/theano-users/7Poq8BZutbY/rNCIfvAEAwAJ). There have been some attempts in recreating DeepSurv in other DL platforms, such as [czifan's `DeepSurv.pytorch`](https://github.com/czifan/DeepSurv.pytorch). However, given its popularity and ease of use, I think TensorFlow 2's Keras is a great option for this task.

[mexchy1000 created `DeepSurv_Keras`](https://github.com/mexchy1000/DeepSurv_Keras). However, it is a very raw prototype: it is not properly documented nor validated. Moreover, it is not being actively supported anymore. Therefore, I used it as a rough starting point for the development of DeepSurvK.

This is my first Python package. I am sure there are many places where it could be improved. Feedback is always welcome!

## :tada: Features
* Implemented using Keras (using TensorFlow 2)
* Includes the original datasets together with a proper description of the variables
* Designed with data as pandas DataFrames in mind
* Visualization tools for the most common plots for fast and easy exploration and prototyping
* Treatment recommender
* (Basic) hyperparameter optimization using grid and randomized search

## :bookmark_tabs: Documentation
You can find the complete package's documentation [here](https://deepsurvk.readthedocs.io). Unfortunately, I haven't had as much time as I would like to work on it. Alternatively, I strongly recommend you take look at the [example notebooks](https://github.com/arturomoncadatorres/deepsurvk/tree/master/examples).

## :page_with_curl: License
This package uses the MIT license

## :black_nib: References
If you are using DeepSurvK, please cite the original DeepSurv paper, as well as the current repository as follows:

> * Katzman, Jared L., et al. ["DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network."](https://link.springer.com/article/10.1186/s12874-018-0482-1) BMC medical research methodology 18.1 (2018): 24. [[BibTeX](https://scholar.googleusercontent.com/scholar.bib?q=info:hG13Z0IGDPkJ:scholar.google.com/&output=citation&scisdr=CgXVK4mOEOOa6e7oHyc:AAGBfm0AAAAAXxbtByd6uXB8fbxpWDom9eCJp71TAtUO&scisig=AAGBfm0AAAAAXxbtB35QPVsdnSAHsADGSX408btb6Gvf&scisf=4&ct=citation&cd=-1&hl=en)]
> * Arturo Moncada-Torres. DeepSurvK. Accessed on [MONTH, 20XX].

## :label: Credits
This package was developed in [Spyder](https://www.spyder-ide.org/) (a fantastic open-source Python IDE) using [Cookiecutter](https://github.com/cookiecutter/cookiecutter) and the [`arturomoncadatorres/cookiecutter-pypackage` project template](https://github.com/arturomoncadatorres/cookiecutter-pypackage).


