Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs.
Harini Suresh, Kathleen M. Lewis, John V. Guttag, Arvind Satyanarayan.
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle.
ACM conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO ’21).
Harini Suresh and John Guttag
[paper] [SERC case study version][talk]
Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs.
CHI Conference on Human Factors in Computing Systems (CHI ’21).
Harini Suresh, Steven R. Gomez, Kevin K. Nam, Arvind Satyanarayan
[paper] [talk] [interactive vis]
Do as AI say: susceptibility in deployment of clinical decision-aids.
npj Digital Medicine, 2021.
Susanne Gaube✧, Harini Suresh✧, Martina Raue, Alexander Merritt, Seth J. Berkowitz, Eva Lermer, Joseph F. Coughlin, John V. Guttag, Errol Colak, Marzyeh Ghassemi (✧ = equal contribution)
Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU.
Conference on Knowledge Discovery and Data Mining (KDD 2018).
Harini Suresh✧, Jen Gong✧, John Guttag (✧ = equal contribution)
Racial Disparities and Mistrust in End-of-Life Care.
Machine Learning for Healthcare Conference (MLHC 2018).
Willie Boag, Harini Suresh, Leo Celi, Peter Szolovits and Marzyeh Ghassemi.
Clinical Event Prediction and Understanding using Neural Networks.
Machine Learning for Healthcare Conference (MLHC 2017).
Harini Suresh, Nathan Hunt, Alistair Johnson, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi.
Feminicide & Machine Learning: Detecting Gender-based Violence to Strengthen Civil Sector Activism.
Mechanism Design for Social Good Workshop (MD4SG 2020). New Horizons Award for Most Inspiring Paper
Catherine D’Ignazio, Helena Suarez Val, Silvana Fumega, Harini Suresh, Isadora Cruxen, Wonyoung So, Maria De Los Angeles Martinez and Mariel Garcia-Montes
Modelling Mistrust in End-of-Life Care.
Fairness, Accountability, and Transparency in Machine Learning Workshop, ICML 2018.
Willie Boag, Harini Suresh, Leo Celi, Peter Szolovits and Marzyeh Ghassemi
Disparities in the Performance of Natural Language Processing Tools.
Women in Machine Learning (WiML) Workshop, NIPS 2017.
Harini Suresh✧, Divya Shanmugam✧, John Guttag (✧ = equal contribution)
The Use of Autoencoders for Discovering Patient Phenotypes.
Machine Learning for Healthcare Workshop, NeurIPS 2016.
Harini Suresh, Peter Szolovits, Marzyeh Ghassemi.
Feature Representations for Predicting ICU Mortality
SuperUROP thesis, Computational Biophysics Group, MIT RLE