This course introduces students to data science for good decision-making in the healthcare industry. It prepares health informatics in the data analytics domain, including statistical analysis, data mining, text analytics, and predictive analytics.
For information regarding prerequisites for this course, please refer to the Academic Course Catalog.
The primary goal of this course to introduce the student to analytics as well as statistics in healthcare. This course will provide the foundation in statistical analysis which will serve as the cornerstone for the capstone project. Assessments focus on developing appropriate research questions and solving them through rigorous statistical analysis.
Measurable Learning Outcomes
Upon successful completion of this course, the student will be able to:
- Discuss the relevance of course material and the use of health informatics to a biblical worldview.
- Explain information technology standards surrounding data analytics in healthcare.
- Compare data mining algorithms in healthcare.
- Produce intelligent decision-making data using predictive models.
- Conduct a predictive analytics project that ranges from defining a health problem to model implementation.
Textbook readings and lecture presentations
Course Requirements Checklist
After reading the Course Syllabus and Student Expectations, the student will complete the related checklist found in the Course Overview.
Discussions are collaborative learning experiences. Therefore, the student is required to create a thread in response to the provided prompt for each discussion. Each thread must be at least 500 words and demonstrate course-related knowledge. In addition to the thread, the student is required to reply to 2 other classmates’ threads. Each reply must be at least 350 words. Each thread and reply must include at least 1 biblical integration and 2 peer-reviewed source citations in current APA format in addition to the textbooks.
Tutorial Assignments (5)
The student will complete practical exercises (tutorials) designed to (1) create experience with the software used in the course, (2) provide real-world examples of problems facing a variety of business sectors, (3) build understanding of how to methodically approach solving a data mining hypothesis, and (4) foster a greater understanding of the potential value of corporate data and the impact of big data.
Project Assignments (4)
The student will incorporate all aspects of the course into an integrated, holistic project on data mining. This effort will follow the scientific method outlined in the course textbook and be completed in the following phases.
After reading through all the instructions for the project, the student will submit a 2-page summary outlining the topic he/she would like to address. At least 3 scholarly sources other than the course textbooks must be included, and the intended sources of data must be identified. This summary must demonstrate an overall understanding of the issue the student will investigate and must be submitted to the instructor for approval.
The student will submit a paper of at least 5 pages that outlines the problem, identifies the sources of data, and explains the student’s initial hypothesis. The paper must be in current APA style and include at least 8 scholarly sources other than the course textbooks.
The student will submit a paper of at least 5 pages that outlines the processes implemented for collecting and preparing the data for examination. This phase must be a natural continuation of Phase I, describing in detail what steps the student followed to prepare the data sets used as well as the analytics selected and reasoning for those selections. Identification of key variables and significant descriptive statistics must be included. The paper must be in current APA style, include at least 3 images to augment the content, and include at least 8 scholarly sources other than the course textbooks.
The student will submit a paper of at least 5 pages that builds on the work conducted in Phases I and II. The submitted document will be comprehensive and include the findings, analysis, and next steps recommended as a result of the information generated by the data mining model(s) utilized. The student’s analysis of the data must be presented in a manner that would be appropriate for repeatability by a fellow data miner. The paper must be in current APA style, include at least 3 images to augment the content, and include at least 5 scholarly sources other than the course textbooks.
The student will create a persuasive slide presentation (e.g., PowerPoint) for the purpose of communicating the project (Phases I–III) and the recommendations coming from this effort. The target audience for this information must be consistent with C-level management and other organization decision makers. Details might include cost, schedule, impact, implementation planning, change management issues, risks, benefits, etc. This presentation must include at least 15 slides and at least 3 graphs depicting the model results. The student will also finalize the report coming from the work from Phases I–III into a cohesive product. The report must be at least 15 pages and include at least 4 relevant visualizations. At least 10 scholarly sources other than the course textbooks are required.
Each quiz will cover the Textbook material for the modules in which it is assigned. Each quiz will be open-book/open-notes, contain 15 multiple-choice and true-false questions, and have a 30-minute time limit.