Overview

The “Healthy ML” group at MIT, led by Dr. Marzyeh Ghassemi, focuses on creating and applying machine learning to understand and improve health in ways that are robust, private and fair. Health is important, and improvements in health improve lives. However, we still don’t fundamentally understand what it means to be healthy, and the same patient may receive different treatments across different hospitals or clinicians as new evidence is discovered, or individual illness is interpreted.

Unlike many problems in machine learning - games like Go, self-driving cars, object recognition - disease management does not have well-defined rewards that can be used to learn rules. Models must also be “healthy”, in that they should not learn biased rules or recommendations that harm minorities or minoritized populations. The Healthy ML group tackles the many novel technical opportunities for machine learning in health, and works to make important progress with careful application to this domain.

Read more about our Research Directions and Publications.

News

  • We are excited to host the MIT ML+Health Seminar Series this Fall!
  • Aug 2023 - Congratulations to Hyewon, who presented her paper at MLHC 2023!
    • Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals [Paper] [Code]
      Hyewon Jeong, Collin M. Stultz, Marzyeh Ghassemi
  • Jul 2023 - Congratulations to Vinith and Haoran, who presented their papers at ICML 2023! Also, Marzyeh is giving a keynote speech at ICML 2023!
    • When Personalization Harms: Reconsidering the Use of Group Attributes of Prediction [Paper] [Code]
      Vinith M. Suriyakumar, Marzyeh Ghassemi, Berk Ustun
    • Change is Hard: A Closer Look at Subpopulation Shift [Paper] [Code]
      Yuzhe Yang, Haoran Zhang, Dina Katabi, Marzyeh Ghassemi
  • Jun 2023 - Congratulations to Alice and Yuxin on their papers presented at CHIL 2023 and FaccT 2023, respectively!
    • Clinical Relevance Score for Guided Trauma Injury Pattern Discovery with Weakly Supervised β-VAE [Paper] [Code]
      Qixuan Jin, Jacobien H.F. Oosterhoff, Yepeng Huang, Marzyeh Ghassemi, Gabriel A. Brat
    • In the Name of Fairness: Assessing the Bias in Clinical Record De-identification [Paper] [Code]
      Yuxin Xiao, Shulammite Lim, Tom Joseph Pollard, Marzyeh Ghassemi
  • May 2023 - Congratulations to Ming and Aparna on their paper accepted to AIES 2023 and Science Advances! Aparna’s paper received coverage in MIT News!
    • Evaluating the Impact of Social Determinants on Health Prediction [Paper]
      Ming Ying Yang, Gloria Hyunjung Kwak, Tom Pollard, Leo Anthony Celi, Marzyeh Ghassemi
    • Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data [Paper]
      Aparna Balagopalan, David Madras, David H. Yang, Dylan Hadfield-Menell,Gillian K. Hadfield, Marzyeh Ghassemi
  • Apr 2023 - Congratulations to Bret on his new Lancet Digital Health paper on detecting COVID with wearables.
  • Jan 2023 - Congratulations to Taylor on his new TMLR paper on identifying medical dead-ends with Distributional RL.

Joining the Lab

As an MIT undergrad interested in an UROP: Contact Fern Keniston (fern@csail.mit.edu) to determine if there are research slots available for the semester, and schedule a 30 minute session with Dr. Ghassemi.

As an MIT MEng: Contact Fern Keniston (fern@csail.mit.edu) with a topic and research plan that is relevant to the group.

As an external student: Apply for the MIT EECS or IMES PhD programs, select Marzyeh Ghassemi as a PI you are interested in working with.