Informatics and Data Science for Health

Course Description

Who will have a heart attack within the next ten years? How can we improve outcomes for children with autism by coordinating care? What can big omics data tell us about the mechanisms of disease? How can the answers to these questions help us design interventions to provide more effective care to patients? How can data help us better understand health disparities and other public health needs in our community?

Modern knowledge for how to prevent, diagnose, and treat health problems relies on information that originates from a wide range of sources. These include basic science experiments, clinical trials, population surveys, healthcare professionals, and clinically indicated measurements of individual patients through interviews, physical exams, laboratory tests, and imaging. Data science for health is the process of integrating and interpreting these data. Biomedical informatics is the scientific discipline that is focused on transforming these data from information into knowledge to be leveraged by biomedical researchers and healthcare providers to facilitate research and clinical decision making. In this class, you will learn and apply foundational scientific, biomedical, computer science, and mathematics concepts that underpin these disciplines.

In the first week of the course, students will be introduced to the healthcare system and the fields of data science and biomedical informatics. They will learn to interact with the Unix command line and begin programming in Julia, a modern high-performance dynamic language designed for numerical analysis and computational science. Within the first few days of the course, each student will hone in on a research question and identify a data source that they will develop into a final project. Each student will gain experience in developing a functional solution that uses informatics and data science approaches to address a biomedical or health challenge in the real world.

Week two will focus in-depth on topics core to data science and biomedical informatics including standards and interoperability, inferences on data, electronic health records, and data visualization. Students will learn and practice the programming skills required to complete their projects including file input/output functions, basic statistics, and interacting with databases through interactive in-class programming sessions. Daily assignments will include a computational component to build programming skills along with a theoretical component where students will be assigned readings and asked to answer critical thinking questions about the material.

In the final week of the course, students will learn the fundamental components of presenting scientific work including how to write an abstract and prepare presentations for scientific meetings. There will be dedicated class time to work on projects with the support of the instructors and for individualized instruction tailored to the students’ chosen projects. Two Brown faculty guest lectures will share their respective clinical and academic informatics career paths. Students will present final projects to the class that they may develop further after Summer@Brown into submissions for presentation at the American Medical Informatics Association’s Annual Symposium High School Scholars Program. By the end of the course, students will have gained foundational skills for using biomedical and health data that can be used to support biomedical research, medicine, and public health.

By the end of the course students should:
- Be comfortable at the Linux command line
- Be proficient in computer programming
- Get first-hand experience in biomedical and health research
- Understand the scientific method
- Develop writing and presentation skills

Prerequisites: This course is open to all interested in developing computational skills for studying biomedicine and health. High School Biology and Algebra 2 are strongly recommended, but not required. Students will be required to bring a laptop computer to class daily.