BIODS220 (CS271, BIOMEDIN220)
Artificial Intelligence in Healthcare

Winter 2020

Course Description

Healthcare is one of the most exciting application domains of artificial intelligence, with transformative potential in areas ranging from medical image analysis to electronic health records-based prediction and precision medicine. This course will involve a deep dive into recent advances in AI in healthcare, focusing in particular on deep learning approaches for healthcare problems. We will start from foundations of neural networks, and then study cutting-edge deep learning models in the context of a variety of healthcare data including image, text, multimodal and time-series data. In the latter part of the course, we will cover advanced topics on open challenges of integrating AI in a societal application such as healthcare, including interpretability, robustness, privacy and fairness. The course aims to provide students from diverse backgrounds with both conceptual understanding and practical grounding of cutting-edge research on AI in healthcare.

[Interested Stanford students]: Since this is a new course, please fill out this survey to give us more information about the backgrounds of interested students. This will help us prepare a better course for you!

Course Time and Location

Mondays and Wednesdays, 1:30-2:50pm
McCullough 115

Prerequisites

Proficiency in Python, or significant experience with a different programming language and ability to self-learn. Python will be used for homework assignments and the course project. Basic familiarity with college calculus (e.g. Math 19 or 41, comfortable taking derivatives), linear algebra (e.g. Math 51 or EE 103 / CME 103, comfortable with common matrix vector operations and notation), and probability and statistics (e.g. CME 106 or CS 109, comfortable with common probability distributions, mean, standard deviation, etc). Prior experience with machine learning is highly recommended (e.g. comfortable with the framework of machine learning, and prior experience training a machine learning model). Prior experience with deep learning is helpful but not required.

Grading

Tentative breakdown:
Assignment 1: 20%
Assignment 2: 20%
Midterm: 20%
Course project: 40%

Assignments

There will be two homework assignments in the class, each worth 20% of the final grade. A large part of these assignments will include programming and practical exercises to build expertise in using deep learning with medical data.

Midterm

The in-class midterm is worth 20% of the final grade and will test conceptual understanding of medical data types and designing deep learning approaches for working with medical data.

Course Project

The course project is a significant component of the course and will be worth 40% of the final grade. Students will work individually or in teams of up to 3 to develop and implement an AI-based approach to a healthcare problem. The project will span the duration of the quarter and will include a project proposal, milestone report, and final presentation and report.

Tentative Schedule

DateTopic
Lecture 1 Jan 6 (Mon) Course Introduction
Lecture 2 Jan 8 (Wed) Deep Learning Fundamentals: Part 1
Lecture 3 Jan 13 (Mon) Deep Learning Fundamentals: Part 2
Lecture 4 Jan 15 (Wed) Medical Images: Classification
Jan 20 (Mon) MLK Holiday
Lecture 5 Jan 22 (Wed) Medical Images: Detection and Segmentation
Lecture 6 Jan 27 (Mon) Medical Images: Higher-Dimensional and Video Data
Lecture 7 Jan 29 (Wed) Electronic Health Records
Lecture 8 Feb 3 (Mon) Electronic Health Records: Advanced Topics
Lecture 9 Feb 5 (Wed) Genomics
Lecture 10 Feb 10 (Mon) Genomics: Advanced Topics
Lecture 11 Feb 12 (Wed) Time-series and Multimodal Data
Feb 17 (Mon) Presidents' Day Holiday
Lecture 12 Feb 19 (Wed) Unsupervised and Reinforcement Learning
Feb 24 (Mon) In-Class Midterm
Lecture 13 Feb 26 (Wed) Fairness and Transparency
Lecture 14 Mar 2 (Mon) Distributed Computing, Privacy, and Security
Lecture 15 Mar 4 (Wed) Guest Lecture: Special Topics
Lecture 16 Mar 9 (Mon) Guest Lecture: Special Topics
Lecture 17 Mar 11 (Wed) Course Conclusion