BMDS 271: Foundation Models for Healthcare (CS 277, RAD 271)
Stanford University, Winter 2026
Course Description
Generative AI and large-scale self-supervised foundation models are poised to have a profound impact on human decision making across occupations. Healthcare is one such area where such models have the capacity to impact patients, clinicians, and other care providers. In this course, we will explore the training, evaluation, and deployment of generative AI and foundation models, with a focus on addressing current and future medical needs. The course will cover models used in natural language processing, computer vision, and multi-modal applications. We will explore the intersection of models trained on non-healthcare domains and their adaptation to domain-specific problems, as well as healthcare-specific foundation models.
Prerequisites
Familiarity with machine learning principles at the level of CS 229, 231N, or 224N
Time & Location
Mon, Wed 3:00 PM - 4:20 PM at Li Ka Shing Center, Room 130
Instructors
TAs
Policies
- Class Participation (15%): Students are strongly encouraged to attend lectures in person and participate actively by asking questions and offering comments. In-person attendance will be recorded in class via a password-locked Canvas quiz; the password will be announced during lecture. Additional attendance policies are detailed below:
- In-Person Students: In order to receive full credit for class participation, students must obtain 14 attendance points (out of 16 available). Attending an in-person lecture and submitting the quiz counts as 1 attendance point. Students who cannot attend in person may watch the recorded lecture and submit the quiz late (by the Sunday following lecture) for 0.25 attendance points.
- SCPD/HCP Students: In order to receive full credit for class participation, students must obtain 14 attendance points. SCPD/HCP students may watch the recorded lecture and submit the quiz by the Sunday following lecture for 1 attendance point.
- Homework Assignments (40%): This course will include two homework assignments, with each homework assignment making up 20% of the course grade. Each student has a total of three late days that can be used throughout the quarter. After the three late days are used up, each additional day late will result in a 25% reduction in the assignment grade.
- Final Project (45%): Students will form teams and choose from one of the suggested projects or select their own project. We encourage project teams of three to four students each. Teams are expected to work on the research project throughout the second half of the quarter and produce conference-style papers. Each team will present the paper to the entire class on the last scheduled lecture of the quarter. No late days are permitted for the course project.
- Access to Foundation Models: If you do not already have access to frontier language models, we encourage students to sign up for services such as the free Gemini Pro Education Plan. While no specific language model is a requisite for this course, access to strong models could be used as additional resources throughout the course.
- Discussion Platforms: We will be using Ed for all discussions.