61 citations · 321 across the 27 of their papers we have counts for
27 papers
Causal Machine Learning Is Not a Panacea: A Roadmap for Observational Causal Inference in Health
Donna Tjandra, Trenton Chang, Sonali Parbhoo +8
Objective: The growing availability of large-scale observational clinical datasets and challenges in conducting randomized controlled trials have spurred enthusiasm in using causal…
Updating Clinical Risk Stratification Models Using Rank-Based Compatibility: Approaches for Evaluating and Optimizing Clinician-Model Team Performance
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. However, updating a model can i…
Leveraging Factored Action Spaces for Off-Policy Evaluation
Aaman Rebello, Shengpu Tang, Jenna Wiens +1
Off-policy evaluation (OPE) aims to estimate the benefit of following a counterfactual sequence of actions, given data collected from executed sequences. However, existing OPE esti…
Leveraging an Alignment Set in Tackling Instance-Dependent Label Noise
Donna Tjandra, Jenna Wiens
Noisy training labels can hurt model performance. Most approaches that aim to address label noise assume label noise is independent from the input features. In practice, however, l…
Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
Shengpu Tang, Maggie Makar, Michael W. Sjoding +2
Many reinforcement learning (RL) applications have combinatorial action spaces, where each action is a composition of sub-actions. A standard RL approach ignores this inherent fact…
Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose
Harry Rubin-Falcone, Joyce Lee, Jenna Wiens
In time-series forecasting, future target values may be affected by both intrinsic and extrinsic effects. When forecasting blood glucose, for example, intrinsic effects can be infe…
Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning
Trenton Chang, Michael W. Sjoding, Jenna Wiens
As machine learning (ML) models gain traction in clinical applications, understanding the impact of clinician and societal biases on ML models is increasingly important. While bias…
Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure
Sarah Jabbour, David Fouhey, Ella Kazerooni +2
Objective: When patients develop acute respiratory failure, accurately identifying the underlying etiology is essential for determining the best treatment. However, differentiating…
Mind the Performance Gap: Examining Dataset Shift During Prospective Validation
Erkin Ötleş, Jeeheh Oh, Benjamin Li +8
Once integrated into clinical care, patient risk stratification models may perform worse compared to their retrospective performance. To date, it is widely accepted that performanc…
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
Shengpu Tang, Jenna Wiens
Reinforcement learning (RL) can be used to learn treatment policies and aid decision making in healthcare. However, given the need for generalization over complex state/action spac…
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
Jiaxuan Wang, Jenna Wiens, Scott Lundberg
Many existing approaches for estimating feature importance are problematic because they ignore or hide dependencies among features. A causal graph, which encodes the relationships…
Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts
Sarah Jabbour, David Fouhey, Ella Kazerooni +2
While deep learning has shown promise in improving the automated diagnosis of disease based on chest X-rays, deep networks may exhibit undesirable behavior related to shortcuts. Th…
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control
Ian Fox, Joyce Lee, Rodica Pop-Busui +1
People with type 1 diabetes (T1D) lack the ability to produce the insulin their bodies need. As a result, they must continually make decisions about how much insulin to self-admini…
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
Shengpu Tang, Aditya Modi, Michael W. Sjoding +1
Standard reinforcement learning (RL) aims to find an optimal policy that identifies the best action for each state. However, in healthcare settings, many actions may be near-equiva…
AdaSGD: Bridging the gap between SGD and Adam
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…
Advocacy Learning: Learning through Competition and Class-Conditional Representations
Ian Fox, Jenna Wiens
We introduce advocacy learning, a novel supervised training scheme for attention-based classification problems. Advocacy learning relies on a framework consisting of two connected…
Automatically Evaluating Balance: A Machine Learning Approach
Tian Bao, Brooke N. Klatt, Susan L. Whitney +2
Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the fea…
Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
Jeeheh Oh, Jiaxuan Wang, Shengpu Tang +2
Recurrent neural networks (RNNs) are commonly applied to clinical time-series data with the goal of learning patient risk stratification models. Their effectiveness is due, in part…
Leveraging Clinical Time-Series Data for Prediction: A Cautionary Tale
Eli Sherman, Hitinder Gurm, Ulysses Balis +2
In healthcare, patient risk stratification models are often learned using time-series data extracted from electronic health records. When extracting data for a clinical prediction…
Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks
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. This is due, in par…
A Domain Guided CNN Architecture for Predicting Age from Structural Brain Images
Pascal Sturmfels, Saige Rutherford, Mike Angstadt +3
Given the wide success of convolutional neural networks (CNNs) applied to natural images, researchers have begun to apply them to neuroimaging data. To date, however, exploration o…
Deep Multi-Output Forecasting: Learning to Accurately Predict Blood Glucose Trajectories
Ian Fox, Lynn Ang, Mamta Jaiswal +2
In many forecasting applications, it is valuable to predict not only the value of a signal at a certain time point in the future, but also the values leading up to that point. This…
The Advantage of Doubling: A Deep Reinforcement Learning Approach to Studying the Double Team in the NBA
Jiaxuan Wang, Ian Fox, Jonathan Skaza +3
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…
Clinically Meaningful Comparisons Over Time: An Approach to Measuring Patient Similarity based on Subsequence Alignment
Dev Goyal, Zeeshan Syed, Jenna Wiens
Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogen…