6.S897 | Spring 2019 | Graduate

Machine Learning for Healthcare


Ses # Topics Key Dates
1 Introduction: What Makes Healthcare Unique? Problem Set 0 Out
2 Overview of Clinical Care  
3 Deep Dive into Clinical Data

Reading Questions

Problem Set 0 Due

Problem Set 1 Out


Risk Stratification, Part 1

Discussant: Leonard D’Avolio

Reading Questions
5 Risk Stratification, Part 2

Reading Questions

Problem Set 1 Due

6 Physiological Time-Series

Reading Questions

Problem Set 2 Out


Natural Language Processing (NLP), Part 1

Discussant: Katherine Liao

Reading Questions
8 Natural Language Processing (NLP), Part 2

Problem Set 2 Due

Problem Set 3 Out


Translating Technology into the Clinic

Discussant: Adam Wright


Machine Learning for Cardiology

Guest Lecture: Rahul Deo

Reading Questions

Problem Set 3 Due

Problem Set 4 Out

11 Machine Learning for Differential Diagnosis Reading Questions

Machine Learning for Pathology

Guest Lecture: Andy Beck

Reading Questions

Problem Set 4 Due


Machine Learning for Mammography 

Guest Lecture: Connie Lehman, Adam Yala

Reading Questions

Project Proposals Due

14 Causal Inference, Part 1

Reading Questions

Problem Set 5 Out

15 Causal Inference, Part 2 Midsemester Feedback

Reinforcement Learning, Part 1

Guest Lecture: Fredrik Johansson

Reading Questions

Reinforcement Learning, Part 2

Guest Lecture: Barbra Dickerman

Evaluating Dynamic Treatment Strategies

Reading Questions

Problem Set 5 Due

18 Disease Progression & Subtyping, Part 1 Problem Set 6 Out
19 Disease Progression & Subtyping, Part 2  
20 Precision Medicine Problem Set 6 Due
21 Automating Clinical Workflows  

Regulation of ML/AI in the US

Guest Lecture: Andy Coravos

Human Subjects Research

Guest Lecture: Mark Shervey

Reading Questions
23 Fairness  
24 Robustness to Dataset Shift Project Presentations
25 Interpretability Project Reports Due

Learning Resource Types
Lecture Videos
Lecture Notes