6.871/HST.956: Machine Learning for Healthcare

Instructors: David Sontag, Peter Szolovits
Teaching Assistants: Matthew McDermott, Monica Agrawal (Office Hours: TBA)
Graduate level; Units 3-0-9 (counts as an AAGS subject)
Time: Tuesdays & Thursdays, 2:30-4pm
Location: 4-270
Prerequisite: 6.036/6.862 or 6.867 or 9.520/6.860 or 6.806/6.864 or 6.438 or 6.034
Office Hours: Monday (non-holiday) 12:30-2PM, Stata G9 lounge (immediately outside elevators).
If Monday is a university holiday, then Wed 4-6 PM, G9 lounge.
Recitations (optional): Fri 2-3pm in room 1-390
Contact: Piazza
Stellar page: Stellar Page

Course Description | Prerequisite quiz | Schedule | Problem sets | Scribing | Late Policy | Prior Years

Course description

Introduces students to machine learning in healthcare, including the nature of clinical data and the use of machine learning for risk stratification, disease progression modeling, precision medicine, diagnosis, subtype discovery, and improving clinical workflows. Topics include causality, interpretability, algorithmic fairness, time-series analysis, graphical models, deep learning and transfer learning. Guest lectures by clinicians from the Boston area and course projects with real clinical data emphasize subtleties of working with clinical data and translating machine learning into clinical practice. Additional content regarding the course, including information on the final project. will be added soon. Check out the 2019 Course Page for a preview!


Prerequisite quiz

This quiz will not count toward your grade, but will be used by the course staff to check prerequisites (6.036/6.862 or 6.867 or 9.520/6.860 or 6.806/6.864 or 6.438 or 6.034) and to assess students' preparation for this class.

You can take the prerequisite quiz here. If you intend to take this class, you must take this quiz before 11:59 p.m. EST on Tuesday, February 4th, 2020


Schedule

Schedule is subject to change.

Class Date Lecture Materials Assignments
1 Tuesday Feb 04
Introduction: What makes healthcare unique?
2 Thursday Feb 06
Overview of Clinical Care
3 Tuesday Feb 11
Deep Dive into Clinical Data
4 Thursday Feb 13
Risk Stratification
  • Pset 1 Out (Due Monday 2/24, 11:59 p.m.)
Tuesday Feb 18
Monday Schedule - No Class
5 Thursday Feb 20
Learning with Noisy and Censored Labels
6 Tuseday Feb 25
Clinical Natural Language Processing (NLP)
7 Thursday Feb 27
Interpretability
8 Tuesday Mar 3
Learning to Defer & Uncertainty
9 Thursday Mar 5
Small to big Data: Case Studies with Physiological Time-series
10 Tuesday Mar 10
Detecting Dataset Shift
11 Thursday Mar 12
Fairness Pt. 1
12 Tuesday Mar 17
Fairness Pt. 2
13 Thursday Mar 19
Causal Inference: Potential Outcomes, Regression
Tuesday Mar 24
Spring Vacation
Thursday Mar 26
Spring Vacation
14 Tuesday Mar 31
Causal Inference: Propensity Reweighting, Instrumental Variables
15 Thursday Apr 2
Causal Inference: Policy Evaluation
16 Tuesday Apr 7
Off-policy Reinforcement Learning
17 Thursday Apr 9
Guest Lecture: TBA
Tuesday Apr 14
No Class - QUIZ
18 Thursday Apr 16
Guest Lecture: TBA
19 Tuesday Apr 21
Precision Medicine
20 Thursday Apr 23
Disease Progression & Subtyping Pt. 1
21 Tuesday Apr 28
Disease Progression & Subtyping Pt. 2
22 Thursday Apr 30
Differential Diagnosis
23 Tuesday May 5
Automating Clinical Workflows
24 Thursday May 7
Translating Technology into the Clinic
Tuesday May 12
No Class - Final Project Poster Sessions

Problem sets

More problem sets forthcoming.


Scribing

Scribing is one mandatory component of your participation grade. Scribing for a lecture will consist of taking high-quality, detailed notes during the lecture in question then working with your scribing team to compile a polished, electronic version of these notes under our direction.

Full instructions for scribing, including how to sign-up for particular scribe dates, can be found here. Please let us know via Piazza if you have any questions!


Late Policy

(starting for pset1 onwards)

Scenarios:


Prior years of this course