Using R for Healthcare Data Science

Welcome! Vojtech and I are excited to talk to you about ways that we use R to help with our data science and informatics tasks.

Materials

• Powerpoint Presentation
• Introduction to R
• Common Challenges in Data Science
• Case Study 1
• Supplementary Slides for Case Study 1
• Case Study 2
• Working with XML Data in R and ClinicalTrials.gov
• Data Cleaning and Querying with the Drugs@FDA dataset
• Terminology Manipulations Using RxNorm



Outline

---

Part 1: Introduction

• R Installation and Introduction to RStudio
• Overview of R
• Commom Data/Code Repositories (CRAN, GitHub, etc.)
• Common Challenges in Data Science and R Language Solutions
• Data Wrangling (dplyr, tidyr, purrr)
• Data Cleaning (lubridate, stringr)
• Visualization (ggplot, ggvis)
• Interactive Reporting (RMarkdown, Shiny)
-- 5 min Break --

Part 2: Demonstration of Data Science Techniques Using Case Studies

• Case Study 1: The Data Scientist's Workflow
• Doing Reproducible Research with RMarkdown and Knitr
• Getting Data In and Out of R
• Principles of Tidy Data and R Datatypes
• Text Processing in R
• Data Manipulation and Transformation
• Data Analysis and Visualization
• Dynamic Web Applications and Visualizations
• Case Study 2: Using Existing Biomedical Resources in R
• Working with XML Data in R and ClinicalTrials.gov
• Data Cleaning and Querying with the Drugs@FDA dataset
• Terminology Manipulations Using RxNorm

Part 3: Comparing R to Other Platforms

• Comparison to Other Languages
• R Advantages and Disadvantages
• Q&A Discussion