Spring 2024

I 320M Topics in Health Informatics: Machine Learning for Population Health Management

Unique ID: 27459

   Tues
   Thurs

05:00 PM - 06:30 PM  SZB 2.418

DESCRIPTION

Leveraging medical claims data to guide population health interventions, primarily through the use of machine learning models. The course will focus on the data processing pipeline, and no prerequisite knowledge of machine learning models is required

COURSE NOTES

Population health management aims to improve individual health outcomes, improve health equity, and reduce overall cost of care for groups of people. The most successful organization will be those who are able to leverage data in order to improve decision making and guide successful health interventions. The purpose of this course is to equip students with the ability to build machine learning models whose purpose is to guide population health interventions. The course is designed to be truly interdisciplinary, and will combine information from healthcare policy, programming, and statistical methods of learning. The course emphasizes a human-centered approach to data science, with specific emphasis placed on the interpretation of models and the measurement and mitigation of algorithmic bias. This course covers a wide range of topics, all of which are salient for analytic professionals interested in the field of healthcare. By the end of the course, successful student will understand: • How programs of population health management can be applied to patient populations to avoid adverse outcomes, and the role of data in driving program efficiency and effectiveness. • How to leverage SQL to process medical claims records into data appropriate for visualization and predictive analytics. • The role of interpretable machine learning models, and how these models should be assessed for algorithmic bias.

PREREQUISITES

Informatics 310M.

RESTRICTIONS

Registration prioritized for undergraduate Informatics majors through registration period 1, with access being extended to Informatics minors beginning in period 2. Outside students will be permitted to join our waitlists beginning with period 3.