Zobrazeno 1 - 10
of 134
pro vyhledávání: '"Perotte P"'
Shapley values have emerged as a foundational tool in machine learning (ML) for elucidating model decision-making processes. Despite their widespread adoption and unique ability to satisfy essential explainability axioms, computational challenges per
Externí odkaz:
http://arxiv.org/abs/2402.04211
Survival analysis is a widely-used technique for analyzing time-to-event data in the presence of censoring. In recent years, numerous survival analysis methods have emerged which scale to large datasets and relax traditional assumptions such as propo
Externí odkaz:
http://arxiv.org/abs/2311.01660
We present a novel stochastic variational Gaussian process ($\mathcal{GP}$) inference method, based on a posterior over a learnable set of weighted pseudo input-output points (coresets). Instead of a free-form variational family, the proposed coreset
Externí odkaz:
http://arxiv.org/abs/2311.01409
Autor:
Rimma Perotte, Alyssa Berns, Lana Shaker, Chayapol Ophaswongse, Joseph Underwood, Christina Hajicharalambous
Publikováno v:
JMIR Formative Research, Vol 8, p e53314 (2024)
BackgroundIt is vital for residents to have a longitudinal view of their educational progression, and it is crucial for the medical education team to have a clear way to track resident progress over time. Current tools for aggregating resident data a
Externí odkaz:
https://doaj.org/article/ea18d73992e64149a00d15c2b98a8618
Autor:
John P. Kane, Andrew Ames, Raj V. Patel, Kaitlyn Voity, Roland Narine, Rimma Perotte, Simon Gelman, Diana McCarthy, Sondra Maureen Nemetski
Publikováno v:
Journal of the American College of Emergency Physicians Open, Vol 5, Iss 3, Pp n/a-n/a (2024)
Abstract Objectives With the legalization of cannabis in New Jersey on April 21, 2022, including the licensing of cannabis dispensaries, concerns have arisen about potential adverse events related to cannabis use. Here, we explore temporal trends and
Externí odkaz:
https://doaj.org/article/7d55b5ce0d9d4eaf967c2829e62d2fb3
Autor:
Ouyang, David, Theurer, John, Stein, Nathan R., Hughes, J. Weston, Elias, Pierre, He, Bryan, Yuan, Neal, Duffy, Grant, Sandhu, Roopinder K., Ebinger, Joseph, Botting, Patrick, Jujjavarapu, Melvin, Claggett, Brian, Tooley, James E., Poterucha, Tim, Chen, Jonathan H., Nurok, Michael, Perez, Marco, Perotte, Adler, Zou, James Y., Cook, Nancy R., Chugh, Sumeet S., Cheng, Susan, Albert, Christine M.
Background. Pre-operative risk assessments used in clinical practice are limited in their ability to identify risk for post-operative mortality. We hypothesize that electrocardiograms contain hidden risk markers that can help prognosticate post-opera
Externí odkaz:
http://arxiv.org/abs/2205.03242
Autor:
Han, Xintian, Goldstein, Mark, Puli, Aahlad, Wies, Thomas, Perotte, Adler J, Ranganath, Rajesh
Deep models trained through maximum likelihood have achieved state-of-the-art results for survival analysis. Despite this training scheme, practitioners evaluate models under other criteria, such as binary classification losses at a chosen set of tim
Externí odkaz:
http://arxiv.org/abs/2111.08175
Autor:
Pang, Chao, Jiang, Xinzhuo, Kalluri, Krishna S, Spotnitz, Matthew, Chen, RuiJun, Perotte, Adler, Natarajan, Karthik
Publikováno v:
Proceedings of Machine Learning for Health, PMLR 158:239-260, 2021
Embedding algorithms are increasingly used to represent clinical concepts in healthcare for improving machine learning tasks such as clinical phenotyping and disease prediction. Recent studies have adapted state-of-the-art bidirectional encoder repre
Externí odkaz:
http://arxiv.org/abs/2111.08585
Causal inference relies on two fundamental assumptions: ignorability and positivity. We study causal inference when the true confounder value can be expressed as a function of the observed data; we call this setting estimation with functional confoun
Externí odkaz:
http://arxiv.org/abs/2102.08533
Survival analysis models the distribution of time until an event of interest, such as discharge from the hospital or admission to the ICU. When a model's predicted number of events within any time interval is similar to the observed number, it is cal
Externí odkaz:
http://arxiv.org/abs/2101.05346