I'm interested in the societal implications of technology, especially machine learning. At MIT, I'm part of the Clinical and Applied Machine Learning Group, the Visualization Group, and the Data + Feminism Lab. My work aims to help make automated systems more understandable and easier to use responsibly. I've also worked on applications of machine learning in healthcare.
- Harini Suresh, Steven R. Gomez, Kevin K. Nam, Arvind Satyanarayan. 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).
- Susanne Gaube*, Harini Suresh*, Martina Raue, Alexander Merritt, Seth J. Berkowitz, Eva Lermer, Joseph F. Coughlin, John V. Guttag, Errol Colak, Marzyeh Ghassemi.
Do as AI say: susceptibility in deployment of clinical decision-aids. npj Digital Medicine, 2021. (* = equal contribution)
- Harini Suresh, Kathleen M. Lewis, John V. Guttag, Arvind Satyanarayan.
Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs. In Submission.
- Harini Suresh, John Guttag.
A Framework For Understanding Sources of Unintended Consequences in Machine Learning. In Submission.
- Harini Suresh, Natalie Lao, Ilaria Liccardi.
Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making. ACM Conference on Web Science, 2020.
- Harini Suresh*, Jen Gong*, John Guttag.
Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU. Conference on Knowledge Discovery and Data Mining (KDD) 2018, London. ACM Conference Proceedings. (* = equal contribution)
- Willie Boag, Harini Suresh, Leo Celi, Peter Szolovits and Marzyeh Ghassemi. Racial Disparities and Mistrust in End-of-Life Care. Machine Learning for Healthcare Conference 2018, Stanford CA. JMLR Workshop and Conference Track.
- Harini Suresh, Nathan Hunt, Alistair Johnson, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi. Clinical Event Prediction and Understanding using Neural Networks. Machine Learning for Healthcare Conference 2017, Boston MA. JMLR Workshop and Conference Track.
Workshops and Posters
- Catherine D'Ignazio, Helena Suarez Val, Silvana Fumega, Harini Suresh, Isadora Cruxen, Wonyoung So, Maria De Los Angeles Martinez and Mariel Garcia-Montes. 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)
- Willie Boag, Harini Suresh, Leo Celi, Peter Szolovits and Marzyeh Ghassemi. Modelling Mistrust in End-of-Life Care. Fairness, Accountability, and Transparency in Machine Learning Workshop, ICML 2018, Stockholm.
- Harini Suresh*, Divya Shanmugam*, John Guttag. Disparities in the Performance of Natural Language
Processing Tools. Women in Machine Learning (WiML) Workshop, NIPS 2017, Palm Springs CA. (* = equal contribution)
- Harini Suresh, Peter Szolovits, Marzyeh Ghassemi. The Use of Autoencoders for Discovering Patient Phenotypes. Machine Learning for Healthcare Workshop, NIPS 2016, Barcelona.
- Harini Suresh. Feature Representations for Predicting ICU Mortality (SuperUROP thesis, Computational Biophysics Group, MIT RLE)
Invited Talks and Panels
- UCL-Toronto Ethical Innovation for AI workshop (July 2020). Understanding and Preventing Unintended Consequences of ML (talk and panel).
- ACM Conference on Web Science (July 2020). Measuring the Interference of Machine Learning in Human Decision-Making (talk).
- MIT Better World symposium in Atlanta, GA (October 2019). Trust Issues in Machine Learning (talk and panel).
- Fair ML in Health at Data & Society Research Institute in New York, NY (October 2019). Deploying decision-aids: real-world considerations (talk).
- Computational Cultures: Uncommon Knowledge at MIT Department of Philosophy (May 2019). Ethics across disciplines (lightning talk and panel).
- Diversity and Inclusion Symposium by True Blue Inclusion in New York, NY (May 2019). Tackling Harm and Improving Accountability in the Automation of Talent Management (talk and panel).
- Systems that Learn @ CSAIL Annual Meeting (August 2018). Bias in Machine Learning and Applications to Healthcare (talk).
- Machine Learning for Healthcare Conference in Boston, MA (August 2017). Clinical Event Prediction and Understanding using Neural Networks (lightning talk).
- ICU Intervention Prediction: MIT News, NVIDIA, Huffington Post
- Fair ML: MIT News