Course Description

Course Description:
This course introduces the discipline of health informatics and data science to prepare our students as forerunners of the future of digital health care systems. Followed by an overview of the health informatics industry, it covers a broad range of introductory topics related to the context of health care systems, such as the structure of current health care systems, various types of health data, theoretical framework and practice use of quantitative analytic methodologies, and ethics. More specifically, this course will teach important health informatics technologies and standards, such as electronic health records, medical claims data, imaging/free-text clinical notes, patient-reported outcomes, traditional and machine learning-based analytic algorithms, data visualization, and clinical research and experimental procedures.


Class: Tu/Thr 2:30 - 3:45 pm

Eligibility Restriction:
Reasoning Under Certainty (CS240) or Statistics I (STAT515) for undergraduate students. There are no formal prerequisites for graduate students, but informally, you should be familiar with statistics and some machine learning. Knowledge of health data or medicine is not a prerequisite; this course is designed to introduce the concepts of health and medical data.

Credit: 3 credits.

Course Objectives:

  • To become health data literate
  • To understand the fundamental representations of medical and health-related data
  • To understand key data-driven computing concepts to extract clinically relevant information from various types of medical/healthcare data
  • To understand the fundamentals of biostatistics; to learn important ethics related to handling medical/health data

Course Syllabus

This is subject to alteration, depending on the pacing of the course and student abilities.

  • Introduction / Overview of Health Data Science
  • Study Design and Statistics
  • Health Informatics: Medical Claims Data and Codes
  • In-Class Midterm
  • Health Informatics: EMR Data and Methods
  • Clinical Assessment Measures
  • Digital/Mobile Health Informatics
  • Data Visualization
  • Ethics
  • Final Project

Class Policies

Lectures: Attendance is required only for lectures that involve in-class activities. Missing the lectures that require in-class activities will result in grade deduction in the associated assignments unless the reason for the absence complies with the University's Class Absence Policy.

Assignments: Homework exercises are chiefly for student benefit. Homework counts for 40% of the grade. Students may collaborate with each other, but not more than three students per group, when doing assignments. Students must inform the instructors with whom they are collaborating. Homework will be accepted on Gradescope with a 50% penalty if turned in within the first 24 hours. It will not be accepted later without instructor permission under the University's Class Absence Policy.

Exams: There will be an in-class midterm. They will be closed-book but a one-page equation sheet will be allowed. No makeup exams will be given except under extreme circumstances (strictly according to the University's Class Absence Policy) in which case students must give the instructors notice well before the exam if possible.

Final Project: Groups of 2-3 students will choose a topic of a final project (data analysis) related to the course materials and present a summary of the work at the end of the course. Each group will have 15-20 minutes to present the overview and constructive criticism of the literature review.

Breakdown of Assignemtns/Topics/Exams

Component Fraction of Grade
Assignment 30%
Midterm Exam 40%
Final Project 30%