Machine Learning Projects in Healthcare

XBIOMEDIN215

Stanford School of Engineering, Stanford School of Medicine

Solve real-world healthcare challenges using machine learning. Modeled after the popular BIOMEDIN215 Stanford graduate course, this professional course explores the unique data challenges of the healthcare industry and how machine learning can be applied to help solve them. In this course, we introduce methods for using large-scale electronic medical records data for machine learning, applying text mining to medical records, and for using ontologies for the annotation and indexing of unstructured content as well as for intelligent feature engineering.

Throughout the course, you will work through interactive exercises and case studies, attend live webinars from Stanford faculty and guest speakers, receive ongoing feedback from our course team, and collaborate with your fellow learners. Gain the real-world skills you need to run your own machine learning projects in industry.

  • Work with healthcare data and how to use data to conduct research studies
  • Differentiate between categories of research questions and the study designs used to address them
  • Describe common healthcare data sources and their advantages and limitations relative to different research questions
  • Extract and transform various kinds of clinical data to create analysis-ready datasets
  • Execute tasks involving data manipulation and analysis

What You Need to Get Started

  • We will use the R programming language for homework assignments. Although familiarity with R is strongly suggested but not required, you are required to have some programming experience. Packages dplyr, glmnet, ggplot, or tidyr will be particularly helpful.
  • Some statistical theory will be reviewed in-class, but our focus will be on elementary Machine Learning and how to correctly interpret results. You should have some understanding of statistical inference and predictive modeling before starting the course.
  • Interest, experience, and/or knowledge in Medicine and/or the healthcare system is helpful
  • This course expands upon the AI in Healthcare specialization program and provides a more intermediate level experience with a deeper dive into the content. Prior completion or familiarity with the program is strongly encouraged but not required.