NURS 6411: Information and Knowledge Management | Week 

How can data mining and data warehousing help your health care organization?

Consider the example of Charlotte, who is an informatics analyst working for a multi-state chain of hospitals. The executives to whom she reports have asked her to identify how much time it takes for the different insurance companies with whom they do business to make payments on claims. She has been instructed to pay close attention to claims processed between February 2010 and March 2011. In order to address this task efficiently, Charlotte uses her organization’s data warehousing system, which maintains a centralized source of copies of claims, regardless of the originating hospital. After accessing the database, Charlotte applies data mining techniques to generate new correlations between payment speed, insurance companies, and other variables unique to that time period. Due to her organization’s data mining and warehousing capabilities, Charlotte was able to easily identify the amount of time it took for insurance companies to make payments, as well as speculate on the cause of delays.

Charlotte’s case is just one illustration of the benefits that data warehousing and data mining present to health care organizations.

This week, you examine the relationship between data warehousing and data mining and how they can be applied to benefit health care organizations.

Learning Objectives – NURS 6411:Week 9: Information to Knowledge: Data Mining and Warehousing

Students will:

• Contrast guided data mining with automated data mining
• Assess how health care data should be warehoused to allow for data mining
• Formulate strategies for addressing concerns about of data mining

Learning Resources

Note: To access this week’s required library resources, please click on the link to the Course Readings List, found in the Course Materials section of your Syllabus.

Required Readings

Coronel, C. & Morris, S. (2017). Database systems: Design, implementation, and management (12th ed.). Boston, MA: Cengage Learning.

• Chapter 13, “Business Intelligence and Data Warehouses” (pp. 589-636)This chapter explores data warehousing and how it improves organizational decision making. It also evaluates how, in some situations, the internet may affect data storage and assessments.

Kristianson, K. J., Ljunggren, H., & Gustafsson, L. L. (2009). Data extraction from a semi-structured electronic medical record system for outpatients: A model to facilitate the access and use of data for quality control and research. Health Informatics Journal, 15(4), 305–319.

In this article, the authors demonstrate the importance of structuring diagnostic data for optimum data extraction and patient care. In addition, they evaluate the efficiency of data management standards in electronic medical records (EMRs).

Kulkarni, M. (2010). A case-based data warehousing courseware. 2010 IEEE International Conference on Information Reuse and Integration (IRI), 245–248.

This article evaluates how beginning designers can learn and implement key concepts of data warehousing. The method highlighted here is hands on and involves the creation of a warehouse tailored to suit a specific data set.

Jukic, N., & Nicholas, J. (2010). A framework for collecting and defining requirements for data warehousing projects. Journal of Computing & Information Technology, 18(4), 377–384.

This article proposes a database framework that is standardized to suit various data processing applications. The authors highlight the planning steps for data warehouses and explore methods for creating a database framework that will suit the needs of the end-users.

Hey, T. (2010). The big idea: The next scientific revolution. Harvard Business Review, 88(11), 56–63.

The author of this article explains how applying machine learning in data analysis can produce scientific discoveries and accurate predictions. The article describes several successful applications of machine learning across the domains of health care, oceanography, business, and more.

McAfee, A. (2011). What every CEO needs to know about the cloud. Harvard Business Review, 89(11), 124–132. Retrieved from https://hbsp.harvard.edu/tu/da322771

This article highlights the benefits that cloud computing provides for all business organizations. The author addresses the transition into the widespread use of cloud technology while debunking common criticisms about its usability and security.

Required Media

Laureate Education, Inc. (Executive Producer). (2012). Data Mining and Data Warehousing. Baltimore, MD: Author.

This multimedia piece describes data warehousing and data mining. It highlights their interrelationship and role in the storage and access of data in databases.

Note: The approximate length of this media piece is 5 minutes. Please click on the following link for the transcript: Transcript(PDF).

Discussion: Data Mining in Health Care

As discussed in this week’s readings, data warehousing is a method of data storage that allows for streamlined data management and retrieval. Data mining software aids in clarifying the relationships between stored data and assists in retrieving specific information as needed. In health care organizations, the information this process yields can be used to cut costs and improve patient care.

For this Discussion, you explore the concept of data mining from a health care perspective.

To prepare:

• What are the potential benefits of using data mining in health care?
• Review the information in the Learning Resources on the different types of data warehousing and how the one selected impacts data mining.
• Review the Hey article, “The Next Scientific Revolution.” Consider how data mining through machine learning can be applied to health care.
• Read the section on data mining on pp. 671-673 in the course text, Database Systems: Design, Implementation, and Management and consider how it connects to the content in the Hey article. According to the text, are the data mining techniques Hey describes guided or automated?
• Using the Walden Library, locate at least one specific example of each type of data mining (guided and automated) in health care. The examples you identify should be different from the examples discussed in the Hey article.
• Reflect on your initial impressions of automated data mining in health care. What are your thoughts on applying this type of data mining to patient care? Consider possible drawbacks of both guided and automated data mining. What approaches and strategies could be used to address those concerns?
• Consider any ethical ramifications of using data mining or machine learning as a tool for prognosis.

 

By Day 3 NURS 6411:Week 9: Information to Knowledge: Data Mining and Warehousing

Post an analysis of how data mining can be beneficial to a health care system. Assess how the type of data warehousing used can impact the ability to mine data. Describe examples of the successful use of guided data mining and automated data mining within health care and cite your source. Describe any reservations you have or ethical issues you foresee in using data mining to provide health care information. What approaches and strategies could be used to address those concerns? Justify your responses.

Read a selection of your colleagues’ responses.

By Day 6

Respond to at least two of your colleagues on two different days. Provide additional insights you have on the benefits and drawbacks of using data mining in health care. In addition, outline an approach or strategy that could be used to address the reservations about data mining that your colleagues described. NURS 6411:Week 9: Information to Knowledge: Data Mining and Warehousing.

 

ADDITIONAL INFO 

Data Mining and Warehousing

Introduction

Data Mining is a process for analyzing data that helps businesses gain insight into the underlying structure of their data and predict future events. Data Mining can be used in many different ways, from marketing to research and beyond. In this post we’ll explore what data mining is, how it works, and some examples of where it has been used by businesses around the world!

What is Data Mining?

Data mining is the process of discovering patterns in large data sets.

Data analytics is the broader term for any process that involves analyzing, summarizing and interpreting data. In other words, it includes everything from business intelligence (BI) tools to predictive analytics and machine learning.

What is the difference between Data Mining and Data Warehousing?

Data mining and data warehousing are both important, but they’re not the same.

Data mining is a process of extracting knowledge from data, whereas data warehouse is a structured approach to storing and analyzing large amounts of information in an organized way.

Data mining can be used on its own or as part of a larger project that involves analysis of large amounts of information (such as weather reports). However, it’s more commonly used as part of the overall business process because it helps companies make better decisions about their products and services.

It’s important for businesses to hire professionals who understand both techniques so that they can use one method when necessary without sacrificing accuracy in other areas (for example: if there isn’t enough time or resources available).

Examples of Data Mining

Data mining is a process of extracting insights from data. It’s done by analyzing the patterns that exist in large amounts of structured or unstructured data, using software programs to find relationships between different variables.

Some common uses for data mining include:

• Analyzing customer data to improve marketing campaigns and sales strategies

• Analyzing financial data to determine how much profit each product makes (or loses) over time

• Analyzing sales volumes by product type or geographic region

• Analyzing inventory levels at various times during the year so you can better manage them with fewer errors in your production schedule

How does Data Mining help businesses?

Data mining is a powerful tool that can be used to help businesses make better decisions. By analyzing and understanding large amounts of data, you’ll be able to analyze your customers and products in a way that no other company has been able to do before.

For example, imagine a business is selling clothing products online. The sales team might send out emails offering discounts or free shipping on purchases made during specific times each month—but what if they wanted more information about who was buying from them? How would they know whether their marketing strategies were working?

By using Data Mining techniques like clustering and classification analysis (which allow us see patterns hidden in our data), we can understand who our customers are better than ever before! For example: maybe there’s an issue with shipping costs for some customers; now instead of sending out mass emails asking why people aren’t buying anymore we can use predictive analytics so we know where things stand before anyone else does.”

Benefits of Data Mining

Data mining and warehousing help businesses to make better decisions.

• It helps companies to compete more effectively, by identifying new markets and potential customers.

• It improves customer service, because it allows companies to see what products work best for their customers, and how they can improve those products in future releases. This can be especially important when dealing with large volumes of data (such as images).

• Data mining and warehousing also reduces costs by allowing businesses to automate repetitive tasks like data cleansing or data integration, which would otherwise require manual labor from employees who are trained in these processes but may not have access to all the necessary tools needed for completing these tasks quickly enough without sacrificing accuracy due lack of experience/skill set required for completing such tasks efficiently…

Types of Business Analytics

• Business Analytics is the process of analyzing data to achieve business goals.

• Data Mining is the process of extracting valuable information from large volumes of unstructured data using statistical methods.

• Warehousing refers to storing, retrieving and organizing data in a manner that makes it easily accessible for analysis.

Takeaway:

Data mining is a process of analyzing data to find patterns and trends. It’s the first step in business analytics, and it can be used for a variety of purposes, including predictive modeling and forecasting.

Data mining is used to make predictions about future events like sales or customer behavior. For example: if you know that your customers tend to buy more during certain times of day (say, between 9am and noon), then you might use this information when planning your marketing strategy so that you can hit all those hot spots with ads or promotions at just the right time!

Conclusion

Data mining and warehousing are two important functions that can help your business by providing insights into problems you might not have been able to solve without them. The key takeaway from this article is that there are many different ways to analyze data, and no one approach will be perfect for every type of problem. Each company has different needs when it comes down to analyzing their data, so it’s important for them (as well as anyone else) understand how these techniques work before making any decisions about what technologies will work best for them in their specific situation!