top of page

Wed, 12 Jun



Statistical Methods for Health Equity Webinar: Divya Shanmugam (MIT)

Advancing Equity in Machine Learning for Healthcare

Registration is closed
See other events
Statistical Methods for Health Equity Webinar: Divya Shanmugam (MIT)
Statistical Methods for Health Equity Webinar: Divya Shanmugam (MIT)

Time & Location

12 Jun 2024, 16:00 – 17:00 BST


About the event

The Statistical Methods for Health Equity Series is a monthly online series co-hosted by the Data Science for Health Equity community, the Alan Turing Institute Health Equity Interest Group, and the Department of Statistical Science at University College London.


We are excited to announce the next instalment of our webinar series with speaker Divya Shanmugam from the Massachusetts Institute of Technology.

Specific details on the topic are as below:


Advancing Equity in Machine Learning for Healthcare


The data we collect are often not the data we wish we had. Healthcare data reflects patterns of underdiagnosis, demographic data is shaped by evolving social norms, and benchmark data can be unrepresentative of deployment settings. In this talk, we aim to characterize and mitigate the impact of imperfect data on machine learning models deployed in healthcare. We address two ways in which data can be flawed: imperfect labels and coarse demographics. First, we develop a method to correct for imperfect labels in the form of underdiagnosis between demographic cohorts. We then show how coarse race data obscures disparities across more granular race groups, suggesting existing algorithmic audits may significantly underestimate racial disparities in performance. The talk will conclude with a prospective discussion of how we can better select problems to promote equity in healthcare.

Speaker Biography:

Divya Shanmugam received her PhD at the Massachusetts Institute of Technology, working with Prof. John Guttag on best practices for developing and deploying machine learning models in the presence of unreliable data. She's particularly interested in developing principled methods to address differences between the data we use and the data we wish to have. This work has taken many forms, often grounded in real-world problems drawn from women's health. Results from this work have been published in both machine learning and interdisciplinary fora and has been cited in policy settings, including Norway's Guidelines for the Responsible Use of AI, and in general-interest news sources including the New York Times.


Please direct any questions about the webinar series to Dr Brieuc Lehmann at


  • Event Ticket

    Sale ended



Share this event

bottom of page