Search Results for author:
Found 32 papers, 14 papers with code
Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
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.
Updating Clinical Risk Stratification Models Using Rank-Based Compatibility: Approaches for Evaluating and Optimizing Clinician-Model Team Performance
As data shift or new data become available, updating clinical machine learning models may be necessary to maintain or improve performance over time.
Leveraging Factored Action Spaces for Off-Policy Evaluation
In this work, we propose a new family of "decomposed" importance sampling (IS) estimators based on factored action spaces.
Leveraging an Alignment Set in Tackling Instance-Dependent Label Noise
Overall, our approach improves accuracy while mitigating potential bias compared to existing approaches in the presence of instance-dependent label noise.
Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare
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.
Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose
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.
Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning
Using such biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups.
Combining chest X-rays and electronic health record (EHR) data using machine learning to diagnose acute respiratory failure
Conclusions: Machine learning models combining chest radiographs and EHR data can accurately differentiate between common causes of acute respiratory failure.
Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
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.
Mind the Performance Gap: Examining Dataset Shift During Prospective Validation
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.
mikropml: User-Friendly R Package for Supervised Machine Learning Pipelines
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.
Shapley Flow: A Graph-based Approach to Interpreting Model Predictions
A causal graph, which encodes the relationships among input variables, can aid in assigning feature importance.
Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts
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.
Deep Reinforcement Learning for Closed-Loop Blood Glucose Control
We highlight the flexibility of RL approaches, demonstrating how they can adapt to new individuals with little additional data.
Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies
We analyze the theoretical properties of the proposed algorithm, providing optimality guarantees and demonstrate our approach on simulated environments and a real clinical task.
AdaSGD: Bridging the gap between SGD and Adam
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.
Learning Through Limited Self-Supervision: Improving Time-Series Classification Without Additional Data via Auxiliary Tasks
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.
Deep RL for Blood Glucose Control: Lessons, Challenges, and Opportunities
We highlight the flexibility of RL approaches, demonstrating how they can adapt to new individuals with little additional data.
Advocacy Learning: Learning through Competition and Class-Conditional Representations
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.
Automatically Evaluating Balance: A Machine Learning Approach
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.
Relaxed Parameter Sharing: Effectively Modeling Time-Varying Relationships in Clinical Time-Series
In settings with limited data, relaxed parameter sharing can lead to improved patient risk stratification performance.
Leveraging Clinical Time-Series Data for Prediction: A Cautionary Tale
In healthcare, patient risk stratification models are often learned using time-series data extracted from electronic health records.
Advocacy Learning
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.
Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks
Recently, researchers have started applying convolutional neural networks (CNNs) with one-dimensional convolutions to clinical tasks involving time-series data.
A Domain Guided CNN Architecture for Predicting Age from Structural Brain Images
Our results suggest that lessons learned from developing models on natural images may not directly transfer to neuroimaging tasks.
Deep Multi-Output Forecasting: Learning to Accurately Predict Blood Glucose Trajectories
Overall, the results suggest the efficacy of our proposed approach in predicting blood glucose level and multi-step forecasting more generally.
The Advantage of Doubling: A Deep Reinforcement Learning Approach to Studying the Double Team in the NBA
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?"
Clinically Meaningful Comparisons Over Time: An Approach to Measuring Patient Similarity based on Subsequence Alignment
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).
Learning Credible Models
In this work, we formally define credibility in the linear setting and focus on techniques for learning models that are both accurate and credible.
Contextual Motifs: Increasing the Utility of Motifs using Contextual Data
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.
Patient Risk Stratification for Hospital-Associated C. diff as a Time-Series Classification Task
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.
Active Learning Applied to Patient-Adaptive Heartbeat Classification
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.
