430 citations · 736 across the 15 of their papers we have counts for
4 papers · 1 filter
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Alexander D'Amour, Katherine Heller, Dan Moldovan +37
ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…
Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU
Harini Suresh, Jen J. Gong, John Guttag
Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings. These models are often developed and evaluated on datasets with heter…
Clinical Intervention Prediction and Understanding using Deep Networks
Harini Suresh, Nathan Hunt, Alistair Johnson +3
Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs). This task is complicated by data sources that are noisy, sparse, heterogeneou…
The Use of Autoencoders for Discovering Patient Phenotypes
Harini Suresh, Peter Szolovits, Marzyeh Ghassemi
We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will reac…