DSCI 622: Modeling and Predictive Analytics in Healthcare
Summer 2025
Login
Communication
Annoucements:
  • HW for Module 1.1 has been posted; due May 21 by 11:59PM; See video on how to submit HW (do not put your HW in D2L)
  • Notes for Module 1.2 have been posted

  • Getting started in COLAB: Video
  • Submitting your Homework: Video

  • Submitting your Notes: Video
  • Setup of your StatsClass Account: Video
  • Introduction / Welcome: Video


Course Materials
Module Description Notes Videos
for Notes		 HW
1 1.2: Simple Linear Regression
- Notes
- Files 		Video
1.1: Introduction to Predictive Analytics
- Notes 		Video

Due: 05/21
HW Link


Files


Video Archive
6 Video Module 1 - Part 2: Simple Linear Regression
5 Video Module 1 - Part 1: Introduction to Predictive Analytics
4 Video Submitting Your HW: Shows users how to submit their homework assignments
3 Video Getting Started with Google COLAB
3 Video Submitting Your Notes: Shows users how to submit their online notes
2 Video Account Setup: Shows users how to setup an account at StatsClass.org.
1 Video Introduction / Syllabus


Item Description
Student Accounts In addition to D2L, an account is necessary at Statsclass.org for the submission of your course notes and the homework assignments for this course. The following video describes how a student account can be setup. [Video: Setting up an Account]
Course Notes A set of interactive course notes are being developed for this course. The course notes are divided into modules and parts. These interactive notes may require that you complete various tasks and/or answer questions that are embedded within the notes. After you submit your notes, the answers to questions and/or tasks are provided so that you can check your understanding of the content being covered. [Video: Submitting your Notes ]
Computing Technologies This course will require the use of powerful computing technologies. The Google COLAB framework (with either Python or R) will be used throughout this course. Students in this course typically have a variety of skills/abilities regarding technical computing. As a result, substantial support will be provided for the necessary computing aspects in this course.
HW Submission Most modules will include a homework assignment. The homework assignments will be distributed via Google Docs and completed assignments must be saved to your Google Drive. After completing the assigment, you must login to your student account at StatsClass and submit a sharable link of your assignment. A brief video describing this process is provided here. [Video: Submitting your HW ]
Grades Your grade is determined by the completion and performance of the required work for this course.

You must complete the course notes for each module / part. The course notes will be scored as follows:
  • 0 pts: Did not complete tasks and/or answer questions posed
  • 5 pts: Attempted to successfully complete tasks and/or answer questions posed
After completing the set of course notes for a module / part, you will be required to complete the associated homework assignment for that module. Most assignments will include two parts: 1) a technical component, and 2) a second component for the write up.

- The technical component for each assignment will be worth 5 points and will be graded as follows:
  • 0 pts: Did not make a reasonable attempt to complete the technical component of the assignment
  • 3 pts: Made a reasonable attempt to sufficiently complete the technical component of assignment by the due date
  • 5 pts: Sufficiently completed the technical component of the assignment by the due date
- The Write Up component of each assignment will be worth 10 points. This component will be graded in a more typical fashion with credit/partial credit given. Clear and concise communication is an important element of this component.

Note: You cannot submit homework assignments after solutions have been posted; thus, it is important that you submit your work before the specified deadline for the assignment.

Final grades will be determined using the following scale
  • F: Less than 55%
  • D: 55% - 64.99%
  • C: 65% - 74.99%
  • B: 75% - 84.99%
  • A: 85% and above
Learning Outcomes Students who successfully complete DSCI 622 will be able to:
  1. Discuss the proper use of various statistical models and machine learning algorithms.
  2. Apply unsupervised learning methods to an application in healthcare.
  3. Apply supervised learning methods, i.e. predictive models, to an application in healthcare.
  4. Assess the quality of statistical models and/or machine learning algorithms.
  5. Interpret outcomes from statistical models and/or machine learning algorithms.
  6. Practice taking outcomes from statistical models and/or machine learning algorithms and applying these into decision-making and/or policy development in healthcare.
Syllabus The WSU DSCI 622 course syllabus is available here. DSCI 622 Syllabus