Irene Chen

I am a Ph.D. candidate at MIT CSAIL, advised by Professor David Sontag in the Clinical Machine Learning group. My research focuses on machine learning and its applications to solving important real-world problems including healthcare and fairness.

Prior to MIT, I worked at Dropbox as Data Scientist, Chief of Staff, and Machine Learning Engineer. I graduated from Harvard with a joint AB/SM in Applied Math and Computational Engineering where I researched with Michael Luca and Ben Edelman.

You can email me at iychen [at] mit [dot] edu or reach me on Twitter.



Current research projects include

  1. Congestive Heart Failure: How can we combine electronic health records with mechanistic information to better treat heart failure? What signal do echocardiograms contain? In collaboration with Beth Israel Deaconess Medical Center.
  2. Health Knowledge Graph: How can we build a structure to capture causal information on symptoms and diseases? Can we capture and quantify error in the model?
  3. Fairness in machine learning: How can we make models that represent people of all genders and races? In a world of limited resources, how can we create more inclusive models?


The Disparate Impacts of Medical and Mental Health with AI.
Irene Y. Chen, Peter Szolovits, Marzyeh Ghassemi.
AMA Journal of Ethics, February 2019.

Why Is My Classifier Discriminatory?
Irene Y. Chen, Fredrik D. Johansson, David Sontag.
NeurIPS 2018, Spotlight Presentation (top 4% of submitted papers).
[abstract, pdf, slides, poster]

Sources of Unfairness in Intensive Care Unit Mortality Scores.
Irene Y. Chen, Fredrik D. Johansson, David Sontag.
Women in Machine Learning Workshop at NeurIPS 2017.


For the Spring 2019 semester, I am currently a Teaching Assistant at MIT for Machine Learning for Healthcare.

At Harvard, I was awarded the Derek Bok Center Certificate of Distinction in Teaching for outstanding teaching evaluations. I served on the teaching staff of the following Harvard classes:

Hobbies and interests

In my free time, I enjoy long distance running, reading books, and discussing AI ethics.