1 code implementation • NeurIPS 2023 • Shengpu Tang, Jenna Wiens
In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies.
no code implementations • 10 Aug 2023 • Erkin Ötleş, Brian T. Denton, Jenna Wiens
As data shift or new data become available, updating clinical machine learning models may be necessary to maintain or improve performance over time.
1 code implementation • 13 Jul 2023 • Aaman Rebello, Shengpu Tang, Jenna Wiens, Sonali Parbhoo
In this work, we propose a new family of "decomposed" importance sampling (IS) estimators based on factored action spaces.
1 code implementation • 10 Jul 2023 • Donna Tjandra, Jenna Wiens
Overall, our approach improves accuracy while mitigating potential bias compared to existing approaches in the presence of instance-dependent label noise.
2 code implementations • 2 May 2023 • Shengpu Tang, Maggie Makar, Michael W. Sjoding, Finale Doshi-Velez, Jenna Wiens
We study the theoretical properties of our approach, identifying scenarios where it is guaranteed to lead to zero bias when used to approximate the Q-function.
no code implementations • 17 Apr 2023 • Harry Rubin-Falcone, Joyce Lee, Jenna Wiens
When forecasting blood glucose, for example, intrinsic effects can be inferred from the history of the target signal alone (\textit{i. e.} blood glucose), but accurately modeling the impact of extrinsic effects requires auxiliary signals, like the amount of carbohydrates ingested.
no code implementations • 1 Aug 2022 • Trenton Chang, Michael W. Sjoding, Jenna Wiens
Using such biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups.
1 code implementation • 27 Aug 2021 • Sarah Jabbour, David Fouhey, Ella Kazerooni, Jenna Wiens, Michael W Sjoding
Conclusions: Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of acute respiratory failure.
1 code implementation • 23 Jul 2021 • Shengpu Tang, Jenna Wiens
In this work, we investigate a model selection pipeline for offline RL that relies on off-policy evaluation (OPE) as a proxy for validation performance.
no code implementations • 23 Jul 2021 • Erkin Ötleş, Jeeheh Oh, Benjamin Li, Michelle Bochinski, Hyeon Joo, Justin Ortwine, Erica Shenoy, Laraine Washer, Vincent B. Young, Krishna Rao, Jenna Wiens
In this study, we compare the 2020-2021 ('20-'21) prospective performance of a patient risk stratification model for predicting healthcare-associated infections to a 2019-2020 ('19-'20) retrospective validation of the same model.
1 code implementation • Journal of Open Source Software 2021 • Begüm D. Topçuoğlu, Zena Lapp, Kelly L. Sovacool, Evan Snitkin, Jenna Wiens, Patrick D. Schloss
Machine learning (ML) for classification and prediction based on a set of features is used to make decisions in healthcare, economics, criminal justice and more.
1 code implementation • 27 Oct 2020 • Jiaxuan Wang, Jenna Wiens, Scott Lundberg
A causal graph, which encodes the relationships among input variables, can aid in assigning feature importance.
no code implementations • 21 Sep 2020 • Sarah Jabbour, David Fouhey, Ella Kazerooni, Michael W. Sjoding, Jenna Wiens
This paper studies the case of spurious class skew in which patients with a particular attribute are spuriously more likely to have the outcome of interest.
no code implementations • 18 Sep 2020 • Ian Fox, Joyce Lee, Rodica Pop-Busui, Jenna Wiens
We highlight the flexibility of RL approaches, demonstrating how they can adapt to new individuals with little additional data.
1 code implementation • ICML 2020 • Shengpu Tang, Aditya Modi, Michael W. Sjoding, Jenna Wiens
We analyze the theoretical properties of the proposed algorithm, providing optimality guarantees and demonstrate our approach on simulated environments and a real clinical task.
no code implementations • 30 Jun 2020 • Jiaxuan Wang, Jenna Wiens
In the context of stochastic gradient descent(SGD) and adaptive moment estimation (Adam), researchers have recently proposed optimization techniques that transition from Adam to SGD with the goal of improving both convergence and generalization performance.
no code implementations • 25 Sep 2019 • Ian Fox, Harry Rubin-Falcone, Jenna Wiens
We explore a novel self-supervision framework for time-series data, in which multiple auxiliary tasks (e. g., forecasting) are included to improve overall performance on a sequence-level target task without additional training data.
no code implementations • 25 Sep 2019 • Ian Fox, Joyce Lee, Rodica Busui, Jenna Wiens
We highlight the flexibility of RL approaches, demonstrating how they can adapt to new individuals with little additional data.
no code implementations • 7 Aug 2019 • Ian Fox, Jenna Wiens
Advocacy learning relies on a framework consisting of two connected networks: 1) $N$ Advocates (one for each class), each of which outputs an argument in the form of an attention map over the input, and 2) a Judge, which predicts the class label based on these arguments.
no code implementations • 7 Jun 2019 • Tian Bao, Brooke N. Klatt, Susan L. Whitney, Kathleen H. Sienko, Jenna Wiens
Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments outside of the clinic.
1 code implementation • Machine Learning for Healthcare 2019 2019 • Jeeheh Oh, Jiaxuan Wang, Shengpu Tang, Michael Sjoding, Jenna Wiens
In settings with limited data, relaxed parameter sharing can lead to improved patient risk stratification performance.
no code implementations • 29 Nov 2018 • Eli Sherman, Hitinder Gurm, Ulysses Balis, Scott Owens, Jenna Wiens
In healthcare, patient risk stratification models are often learned using time-series data extracted from electronic health records.
no code implementations • 27 Sep 2018 • Ian Fox, Jenna Wiens
In contrast to a standard network, in which all subnetworks are trained to jointly cooperate, we train the Advocates to competitively argue for their class, even when the input belongs to a different class.
no code implementations • 21 Aug 2018 • Jeeheh Oh, Jiaxuan Wang, Jenna Wiens
Recently, researchers have started applying convolutional neural networks (CNNs) with one-dimensional convolutions to clinical tasks involving time-series data.
1 code implementation • 11 Aug 2018 • Pascal Sturmfels, Saige Rutherford, Mike Angstadt, Mark Peterson, Chandra Sripada, Jenna Wiens
Our results suggest that lessons learned from developing models on natural images may not directly transfer to neuroimaging tasks.
1 code implementation • 14 Jun 2018 • Ian Fox, Lynn Ang, Mamta Jaiswal, Rodica Pop-Busui, Jenna Wiens
Overall, the results suggest the efficacy of our proposed approach in predicting blood glucose level and multi-step forecasting more generally.
1 code implementation • 8 Mar 2018 • Jiaxuan Wang, Ian Fox, Jonathan Skaza, Nick Linck, Satinder Singh, Jenna Wiens
During the 2017 NBA playoffs, Celtics coach Brad Stevens was faced with a difficult decision when defending against the Cavaliers: "Do you double and risk giving up easy shots, or stay at home and do the best you can?"
no code implementations • 2 Mar 2018 • Dev Goyal, Zeeshan Syed, Jenna Wiens
Applied to the task of stratifying patients for risk of progression to probable Alzheimer's Disease, our approach outperforms models that use only snapshot data (AUROC of 0. 839 vs. 0. 812) and models that use global alignment techniques (AUROC of 0. 822).
1 code implementation • 8 Nov 2017 • Jiaxuan Wang, Jeeheh Oh, Haozhu Wang, Jenna Wiens
In this work, we formally define credibility in the linear setting and focus on techniques for learning models that are both accurate and credible.
no code implementations • 6 Mar 2017 • Ian Fox, Lynn Ang, Mamta Jaiswal, Rodica Pop-Busui, Jenna Wiens
Applied to both simulated and real physiological data, our proposed approach improves upon existing motif methods in terms of the discriminative utility of the discovered motifs.
no code implementations • NeurIPS 2012 • Jenna Wiens, Eric Horvitz, John V. Guttag
A patient's risk for adverse events is affected by temporal processes including the nature and timing of diagnostic and therapeutic activities, and the overall evolution of the patient's pathophysiology over time.
no code implementations • NeurIPS 2010 • Jenna Wiens, John V. Guttag
While clinicians can accurately identify different types of heartbeats in electrocardiograms (ECGs) from different patients, researchers have had limited success in applying supervised machine learning to the same task.