| A framework for understanding sources of harm throughout the machine learning life cycle H Suresh, J Guttag Equity and access in algorithms, mechanisms, and optimization, 1-9, 2021 | 520* | 2021 |
| Underspecification presents challenges for credibility in modern machine learning A D'Amour, K Heller, D Moldovan, B Adlam, B Alipanahi, A Beutel, ... The Journal of Machine Learning Research 23 (1), 10237-10297, 2022 | 465 | 2022 |
| Clinical intervention prediction and understanding with deep neural networks H Suresh, N Hunt, A Johnson, LA Celi, P Szolovits, M Ghassemi Machine Learning for Healthcare Conference, 322-337, 2017 | 211* | 2017 |
| Do as AI say: susceptibility in deployment of clinical decision-aids S Gaube, H Suresh, M Raue, A Merritt, SJ Berkowitz, E Lermer, ... NPJ digital medicine 4 (1), 31, 2021 | 141 | 2021 |
| Learning tasks for multitask learning: Heterogenous patient populations in the icu H Suresh, JJ Gong, JV Guttag Proceedings of the 24th ACM SIGKDD International Conference on Knowledge …, 2018 | 79 | 2018 |
| Beyond expertise and roles: A framework to characterize the stakeholders of interpretable machine learning and their needs H Suresh, SR Gomez, KK Nam, A Satyanarayan Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems …, 2021 | 66 | 2021 |
| Orientation‐Specific Attachment of Polymeric Microtubes on Cell Surfaces JB Gilbert, JS O'Brien, HS Suresh, RE Cohen, MF Rubner Advanced Materials 25 (41), 5948-5952, 2013 | 42 | 2013 |
| Use of machine-learning algorithms to determine features of systolic blood pressure variability that predict poor outcomes in hypertensive patients RC Lacson, B Baker, H Suresh, K Andriole, P Szolovits, E Lacson Jr Clinical kidney journal 12 (2), 206-212, 2019 | 38 | 2019 |
| The use of autoencoders for discovering patient phenotypes H Suresh, P Szolovits, M Ghassemi arXiv preprint arXiv:1703.07004, 2017 | 30 | 2017 |
| Misplaced trust: Measuring the interference of machine learning in human decision-making H Suresh, N Lao, I Liccardi 12th ACM Conference on Web Science, 315-324, 2020 | 28 | 2020 |
| Semi-supervised biomedical translation with cycle wasserstein regression GANs M McDermott, T Yan, T Naumann, N Hunt, H Suresh, P Szolovits, ... Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 28 | 2018 |
| Intuitively assessing ml model reliability through example-based explanations and editing model inputs H Suresh, KM Lewis, J Guttag, A Satyanarayan 27th International Conference on Intelligent User Interfaces, 767-781, 2022 | 16 | 2022 |
| Understanding potential sources of harm throughout the machine learning life cycle H Suresh, J Guttag MIT Case Studies in Social and Ethical Responsibilities of Computing 8, 2021 | 15 | 2021 |
| Racial disparities and mistrust in end-of-life care W Boag, H Suresh, LA Celi, P Szolovits, M Ghassemi Machine Learning for Healthcare Conference, 587-602, 2018 | 13 | 2018 |
| Feminicide & machine learning: detecting gender-based violence to strengthen civil sector activism C D’Ignazio, HS Val, S Fumega, H Suresh, I Cruxên | 10 | 2020 |
| Non-task expert physicians benefit from correct explainable AI advice when reviewing X-rays S Gaube, H Suresh, M Raue, E Lermer, TK Koch, MFC Hudecek, ... Scientific reports 13 (1), 1383, 2023 | 6 | 2023 |
| Tech Worker Organizing for Power and Accountability W Boag, H Suresh, B Lepe, C D'Ignazio 2022 ACM Conference on Fairness, Accountability, and Transparency, 452-463, 2022 | 6 | 2022 |
| Feminicide and counterdata production: Activist efforts to monitor and challenge gender-related violence C D'Ignazio, I Cruxên, HS Val, AM Cuba, M García-Montes, S Fumega, ... Patterns 3 (7), 100530, 2022 | 4 | 2022 |
| Improved Text Classification via Test-Time Augmentation H Lu, D Shanmugam, H Suresh, J Guttag arXiv preprint arXiv:2206.13607, 2022 | 4 | 2022 |
| Modeling mistrust in end-of-life care W Boag, H Suresh, LA Celi, P Szolovits, M Ghassemi arXiv preprint arXiv:1807.00124, 2018 | 4 | 2018 |
