Giter Site home page Giter Site logo

chethanmysore / ship-cohort-study Goto Github PK

View Code? Open in Web Editor NEW
1.0 3.0 0.0 2.41 MB

Interpretable Machine Learning to understand Participant Evolution in Longitudinal Cohort Study Data

R 100.00%
interpretable-machine-learning participant-evolution r plumber-api ship-cohort-study

ship-cohort-study's Introduction

ShipStudyApi

Overview

ShipCohortStudy is a project aimed at using Interpretable Machine Learning to understand participant evolution in longitudinal cohort study data. ShipStudyApi is a restful service that exposes http endpoints to visualize the results of rulefit model built on SHIP dataset. Additionally, evoxploit package is used to augment the dataset with evolutionary features (Niemann et al., 2015) and rules extracted from building random forest on the dataset (Friedman et al., 2008). The feature selection is then performed using Least Absolute Shrinkage and Selection Operator(LASSO) to obtain minimal set of important features (Friedman et al., 2009). The api caters to a visualization dashboard that explores the model results dynamically and interactively.
Checkout Dashboard Here

Tasks

  • Measure the influence of each evolution feature on the predicted class.
  • Evaluate the merit of an evolution feature towards classification accuracy.
  • Analyse the minimal change in the participant such that the predicted class label changes.
  • Identify the minimal set of evolution features that would result in better predictive performance.

Running Application

  • Navigate to cloned repository / project directory and run the following command
Rscript src/R/app.R <input_dataset_path>
  • The model building might take from 15 to 30 mins depending on the machine performance.
  • After running the above command, the api service will be available from http://localhost:3000/__swagger__/

Ship-Study-Api

Bibliography

  • (Niemann et al., 2015) Uli Niemann, Tommy Hielscher, Myra Spiliopoulou, Henry Völzke, and Jens-Peter Kühn. "Can we classify the participants of a longitudinal epidemiological study from their previous evolution?" Proc. of IEEE Computer-Based Medical Systems, 121-126, 2015.
  • (Friedman et al., 2008) Friedman, Jerome H.; Popescu, Bogdan E. Predictive learning via rule ensembles. Ann. Appl. Stat. 2 (2008), no. 3, 916--954. doi:10.1214/07-AOAS148.
  • (Friedman et al., 2009) Friedman, Jerome, Trevor Hastie, and Robert Tibshirani. “The elements of statistical learning”.

ship-cohort-study's People

Contributors

ashwinidathatri avatar chethanmysore avatar sinchanabhat avatar

Stargazers

 avatar

Watchers

 avatar  avatar  avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.