ship-cohort-study

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

Tasks

Design and implementation of a visual exploration tool which would include features to :

• 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.

R Libraries Used:

• tidyverse
• testthat
• evoxploit : https://github.com/unmnn/evoxploit
• rmarkdown
• ggplot2