Healthy ML Lab

The Machine Learning for Health group targets "Healthy ML", focusing on creating applying machine learning to understand and improve health.

We believe that 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. Health is unlike many success stories in machine learning so far - games like Go and self-driving cars - because we do not have well-defined goals that can be used to learn rules. The nuance of health also requires that we keep machine learning models "healthy" - working to ensure that they do not learn biased rules or detrimental recommendations.

Improving health requires targeting and evidence – our group tackles part of this puzzle with machine learning. There are many novel technical opportunities for machine learning in health challenges, and important progress to be made with careful application to domain.

Read more about our Research Directions and Publications.


  • Congratulations to Vinith and Victoria Cheng for each of their first author FaCCT 2021 papers!
  • The ML4H Lab will be moving to MIT's IMES/EECS departments in July 2021 as the "Healthy ML" Lab.



Upcoming Talks

  • Oct 24-27, 2021, Invited Keynote Talk ASTRO Annual Meeting
  • May 19, 2021, MIT Systemic Racism Workshop
  • Apr 12, 2021, Algorithms and Data for Fair and Equitable AI, MIT Jameel Clinic
  • Apr 8-9, 2021, General Chair ACM CHIL 2021
  • Mar 26, 2021, MIT Workshop on Data-driven Decision Making in Socio-Technical Systems
  • Mar 11, 2021 Machine Learning for Health Care Panel, WiDS Cambridge
  • Mar 10, 2021 Keynote Panel - Machine Learning and Health Inequities during COVID, FaccT 2021

Recent Talks

Co-Chair Duke Clinical Research Institute (DCRI) Think Tank on ML and clinical research, January 29-30, 2020, Washington DC.

NeurIPS Workshop Co-Chair at NeurIPS 2019, Dec 9-14, 2019, Vancouver, BC.

Invited Talk at the Global Forum for AI and Humanity at the Global Partnership on AI in Paris, France, October 29, 2019.

Keynote Talk at Machine Learning and the Market for Intelligence conference, The Rotman School, October 24, 2019.

Panelist at "Diversity & Inclusion in a Data-Driven World", 11th annual Connected Health Conference, Boston, MA, Oct. 16-18, 2019.

Fair Health and ML Summit, Data and Society Institute, New York City, Oct 11, 2019.

Toronto Health Data Hackathon Host, Centre for Social Innovation, October 4 - 5, 2019.

Invited Talk at TEDx UofT-Fields Salon, Oct 3, 2019.

Invited Talk at Ethics of AI in Context Series Talk @ University of Toronto Centre for Ethics, Oct 1, 2019.

Invited Talk at "Machine Intelligence in Healthcare: Perspectives on Trustworthiness, Explainability, Usability and Transparency" @ NIH/NCATS Workshop, July 12, 2019.

Keynote at iBest Sympsoium, June 14, 2019.

Invited Talk at "Wrong at the Root: Racial Bias and the Tension Between Numbers and Words in Non-Internet Data" Summer Cluster on Fairness @ Simons Institute, University of Berkeley, June 5, 2019.

Invited talk at Rotman Centre for Health Sector Strategy Conference, May 24, 2019.

Invited talk at Stanford Big Data in Precision Health conference, May 22, 2019.

Prof. Ghassemi hosted the Machine Learning for Health Unconference ( in Spring 2019.

Participant at CIFAR AI for Health (AI4H) Roundtable, led by Dr. Elissa Strome (CIFAR) and Dr. Tim Evans (World Bank), May 13, 2019.

Panelist on Raw Talk Live Event @ JLabs Toronto, May 7, 2019.

Keynote speaker at MIT Club of Toronto AI/ML Talks @ Vector Institute, April 16, 2019.

Inaugural invited talk at Microsoft Research Montreal AI Distinguished Lecture Series @ MILA, March 25, 2019.

Keynote at Women in Data Science (WiDS) Conference @ Stanford, March 4, 2019.