Syllabus
COURSE NUMBER, TITLE:
NRSG 741, Big Data Analytics for Healthcare
PRE-/CO-REQUISITES:
BIOS 500 and 501
CREDIT ALLOCATION:
3 credit hours
COURSE DESCRIPTION
This course will describe the concepts underlying the field of study identified as big data analytics along with its application in healthcare. The theoretical underpinnings of these concepts will be presented along with applications in healthcare, including knowledge discovery, precision medicine/nursing, and the development of targeted interventions to improve health outcomes. Commonly used methods in big data analytics will be reviewed, and the challenges related to gathering, analyzing, visualizing, and interpreting big data will be discussed. Hands-on computer laboratory experience with these techniques relevant to an identified area will be included.
COURSE OBJECTIVES
At the end of this course the student will be able to successfully:
Demonstrate knowledge of the principles undergirding the tools of big data analysis in health related research.
Identify the potential of, and challenges to, incorporating big data analytics to improve the development and testing of precision medicine / nursing interventions.
Understand the principles of reproducible research and implement an appropriate workflow for data analysis and manuscript / report generation.
Effectively critique published research of health related studies conducted by using big data theoretical frameworks and research techniques.
Analyze ethical issues related to the use of big data analytics in health related research
Demonstrate knowledge of how data are gathered, stored, managed, and analyzed for big data analytics.
TEACHING AND LEARNING
This course uses a variety of teaching methods, including readings, case presentations, lectures, practical skills application discussion sessions, simulation, and projects.
EVALUATIONS & GRADING
| Assignment | Points |
|---|---|
| Homework (8 total, 5% each) | 40 points |
| Final Big Data Project (presentation and report) | 60 points (breakdown below) |
| ================================================ | ========= |
| Milestone 1: 1-2 page document describing your idea | 5 points |
| Milestone 2: approximately 10 page document showing here you are going - initial DRAFT report | 10 points |
| Milestone 3: FINAL | |
| - Paper | 20 points |
| - Oral Presentation to class | 15 points |
| - Slide Deck | 10 points |
Class participation is expected.
TEXTBOOKS (Recommended):
- Practical Data Science, Zumel N and Mount J, 2014.
- Book website https://ninazumel.com/practical-data-science-with-r/
TEXTBOOKS (Required):
- R in Action: Data Analysis and Graphics with R, Kabacoff R, 2015.
- Book website https://www.manning.com/books/r-in-action
- Quick-R website
The books listed above are available online through the Emory Safari Books Online site. Use the following URL: http://pid.emory.edu/dzfb2
Other useful texts:
- Modern Data Science with R, Baumer, Kaplan, and Horton, CRC Press
- Text Mining with R, Silge and Robinson, O’Reilly on-line https://www.tidytextmining.com/
- An Introduction to Statistical Learning, James, Witten, Hastie, and Tibshirani, Springer
- R for Data Science, Wickham & Grolemund, O’Reilly on-line https://r4ds.had.co.nz/
- R Markdown: The Definitive Guide, by Yihui Xie, J. J. Allaire, Garrett Grolemund https://bookdown.org/yihui/rmarkdown/
- Dynamic Documents with R and knitr, Second Edition (Chapman & Hall/CRC The R Series) 2nd Edition, by Yihui Xie available at Amazon
- bookdown: Authoring Books and Technical Documents with R Markdown by Yihui Xie https://bookdown.org/yihui/bookdown/
Useful websites:
- Happy Git and GitHub for the useR, by Jenny Bryan, the STAT 545 TAs, Jim Hester https://happygitwithr.com/
- Rmarkdown https://rmarkdown.rstudio.com/
- CRAN: download R and packages https://cran.r-project.org/
- RStudio https://rstudio.com/
- RStudio.cloud https://rstudio.cloud/
- Github https://github.com/
- Git https://git-scm.com/
- Rpubs https://rpubs.com/
- Datacamp https://www.datacamp.com/
COURSE REQUIREMENTS & ASSIGNMENTS
Successful completion of the course objectives will be determined by performance with the following course assignments:
Homeworks - Homework assignments will comprise applications of techniques learned in class to different data sets.
One comprehensive final project – a practicum/exemplar presentation of the student’s skills and knowledge for obtaining, analyzing and presenting results from Big Data sources to address an issue of interest in healthcare.
CLOUD PLATFORMS AND RESOURCES FOR COURSE
During this course, class materials, exercises and assignments will utilize GITHUB repositories. Everyone will need an account created at https://github.com/
RStudio Cloud will also be utilized for some assignments and exercises. Everyone will need an account created at https://rstudio.cloud/
SOFTWARE REQUIREMENTS
The exercises and assignments in this course require use of the R programming language. Two FREE open source software packages must be installed: install the R programming language first and then install the RStudio interface: * R programming language, download from https://cran.r-project.org/ * RStudio IDE (integrated development environment), download RStudio Desktop from https://rstudio.com/products/rstudio/download/#download * GIT, needed to link R projects to Github, https://git-scm.com/
Calendar Schedule for Lectures & Homework
| Session | Date | Topic | Assignment DUE |
|---|---|---|---|
| 1 | 01/15 | Introduction to the Course; What is data science?; R and RStudio; Rmarkdown reports | |
| 2 | 01/22 | Reproducible Research Principles and Pipelines | |
| 3 | 01/29 | Data Wrangling with dplyr [Steve Pittard Guest Lecturer] |
HW 1 |
| 4 | 02/05 | Exploratory Data Analysis [Lisa Elon Guest Lecturer] | Milestone 1 |
| 5 | 02/12 | Text/web scraping and working with text (regular expressions) | HW2 |
| 6 | 02/19 | Microbiome analysis – the DADA2 / Phyloseq pipeline | HW3 |
| 7 | 02/26 | Microbiome analysis – the DADA2 / Phyloseq pipeline (continued) | |
| 8 | 03/04 | More on Data (and code) Wrangling | HW4 |
| 9 | 03/11 | - SPRING BREAK NO CLASS - | |
| 10 | 03/18 | Metabolomics analysis [Rebecca Mitchell Guest Lecturer] | HW5 |
| 11 | 03/25 | Models – Linear and Logistic; Prediction | Milestone 2 |
| 11 | 04/01 | Machine learning – supervised methods [Joyce Ho Guest Lecturer] | HW6 |
| 12 | 04/08 | Machine learning – unsupervised methods | HW7 |
| 13 | 04/15 | Network science | HW8 |
| 15 | 04/22 | To the cloud and beyond - AWS [Roy Simpson Guest Lecturer] | |
| 16 | 04/29 | Project presentations | Milestone 3: [1] Paper; [2] Oral Presentation; and [3] Slides |
Copyright © Melinda Higgins, Ph.D.. All contents under (CC) BY-NC-SA license,
unless otherwise noted.