27 Dec Clean and prepare the data.

Week 1 MS Access (or OpenOffice Base for MAC users): Relational Database

PC Users:

Install Microsoft Access if you don’t already have it (available through your student Microsoft 365 account).

Complete the related MS Access training tutorials located in the Assignment Resources below.

Create a simple relational database using information provided in a data set.

You may use one of the student files for chapter 3 provided in the Doc Sharing blog (Access files end in .mdb), a data set from https://www.data.gov/ or a data set you already have of your own.

Submit a screenshot of your completed database along with your relational database file for grading.

Mac Users:

Download and install OpenOffice Base from the following link: http://www.openoffice.org/product/base.html

View the OpenOffice Base videos located in the Assignment Resources below.

Create a simple relational database using information provided in a data set.

You can find a data set from https://www.data.gov/ or use a data set you already have of your own.

Submit a screenshot of your completed database along with your relational database file for grading.

Week 2 MS Access (or OpenOffice Base for MAC Users): Relational Database Query

PC Users:

Complete the related MS Access query training tutorials located in the Assignment Resources below.

Using the relational database created during the first week, run a query to receive meaningful data output (e.g., running a query to filter patients with a specific diagnosis).

Submit a screenshot and your query results for grading.

Mac Users:

Watch the OpenOffice Base Creating Queries video located in the Assignment Resources below.

Using the relational database created during the first week, run a query to receive meaningful data output (e.g., running a query to filter patients with a specific diagnosis).

Submit a screenshot and your query results for grading.

Week 3 Big Data Use Paper

Research a health-related business that collects big data and explain the following in a two-page paper in APA format:

Give a brief overview of big data.

How do the topics learned in this class relate to big data in health care?

In the use case of the business you researched, what kind of data is collected and what are the advantages of collecting this type of data?

Include 2–3 scholarly resources in APA format. Examples of scholarly sources include professional journal articles and books obtained from library databases, national guidelines, and informatics organizations, published within the last five years.

Week 4 XML Overview Paper and Sample XML Document

Discuss the following in a two-page paper in APA format:

What is XML?

Why use XML?

Create a simple XML document for one of the following:

Patient demographics

Patient allergies

Patient vital signs

Patient serum hemoglobin result

Include 2–3 scholarly resources in APA format. Examples of scholarly sources include professional journal articles and books obtained from library databases, national guidelines, and informatics organizations, published within the last five years.

Week 5 Data Mining Software Exercise

This assignment gives you the opportunity to demonstrate your ability to use data mining software.

Download the program RapidMiner (available for Windows or MAC IOS 10.8+) from: https://rapidminer.com/ and register using your WCU student email. (After the 15-day free trial, you can register for a free education license if you’d like. You’ll receive an email from RapidMiner with instructions.)

When you open the program for the first time, tutorials will automatically come up on the left side of the platform’s screen. If you lose this window, click on the file folder icon a the top and choose the Learn option to get it back.

Complete each tutorial within the program and take a screenshot of the results as you finish each one. (list of tutorials provided below)

After you finish the tutorials, submit your screenshots for grading.

Basics

Operators and Processes

Modeling

Accessing Data

Filtering and Sorting

Merging and Grouping

Creating and Removing Columns

Changing Types and Roles

More Modeling

Data Handling

Handle Missing Values

Normalization and Outlier Detection

Pivoting and Renaming

Macros and Sampling

Looping, Branching, and Appending

Writing Data

Modeling, Scoring and Validation

Modeling

Scoring

Test Splits and Validation

Cross Validation

Visual Model Comparison

RapidMiner Server

RapidMiner Radoop

See Assignment Resources below for further RapidMiner support videos.

Week 6 EHR Data Mining Challenges Paper

Discuss the challenges faced by EHR data mining in a two-page paper in APA format. Make sure to include the following:

What is the potential of healthcare data mining?

How can it benefit or improve patient outcomes?

Include 2–3 scholarly resources in APA format. Examples of scholarly sources include professional journal articles and books obtained from library databases, national guidelines, and informatics organizations, published within the last five years.

Week 7 Demonstration of Use of Data Visualization Software

Download a free version of Tableau Desktop for Students (available for Windows PC and MAC OS) at:

https://www.tableau.com/academic/students#product-video Click for more options

View the links listed in the Assignment Resources listed below to learn about Tableau.

Choose a health-related data set from one of the links in the Assignment Resources below.

Follow all eight of the Tableau tutorial steps at the following link to create a meaningful data story from your inputted data set.

http://onlinehelp.tableau.com/current/guides/get-started-tutorial/en-us/get-started-tutorial-home.html

Share your final work in Tableau Public and submit the link along with the link to the data set you used (upload both with the file to Blackboard).

Week 8 Final Data Project

Write a four- to five-page paper that demonstrates comprehension of data mining and data visualization.

Complete the following using a data set from https://www.healthdata.gov/ Click for more options

Clean and prepare the data.

Use any data mining model to extract meaningful data.

Create two data visualizations in Tableau that show data in a meaningful way without information overload.

Explain your data set and describe your data mining model and data visualization technique (two-page maximum).

Submit your data files, links to your visualizations, and your written assignment.

Include the URL of the data set that you downloaded.

Examples of scholarly sources include professional journal articles and books obtained from library databases, national guidelines, and informatics organizations, published within the last five years.