Publications

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

Using labels to limit AI misuse in health

TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods

The limits of fair medical imaging AI in real-world generalization

Test-Time Debiasing of Vision-Language Embeddings

Settling the Score on Algorithmic Discrimination in Health Care

Mental-llm: Leveraging large language models for mental health prediction via online text data

Measuring Stochastic Data Complexity with Boltzmann Influence Functions

MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making

Limiting bias in AI models for improved and equitable cancer care

Improving Subgroup Robustness via Data Selection

Asymmetry in Low-Rank Adapters of Foundation Models

Taking Off with AI: Lessons from Aviation for Healthcare

Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning

Presentation matters for AI-generated clinical advice

Machine learning COVID-19 detection from wearables

Judging facts, judging norms: Training machine learning models to judge humans requires a modified approach to labeling data

In the Name of Fairness: Assessing the Bias in Clinical Record De-identification

Event-Based Contrastive Learning for Medical Time Series

Evaluating the Impact of Social Determinants on Health Prediction

Deep Metric Learning for the Hemodynamics Inference with Electrocardiogram Signals

Considering Biased Data as Informative Artifacts in AI-Assisted Health Care

Clinical Relevance Score for Guided Trauma Injury Pattern Discovery with Weakly Supervised $ $β$ $-VAE

Change is Hard: A Closer Look at Subpopulation Shift

Algorithmic Fairness in Chest X-ray Diagnosis: A Case Study

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adapters

Write It Like You See It: Detectable Differences in Clinical Notes By Race Lead To Differential Model Recommendations

When personalization harms: Reconsidering the use of group attributes in prediction

The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations

The medical algorithmic audit

Semi-Markov Offline Reinforcement Learning for Healthcare

Mitigating the impact of biased artificial intelligence in emergency decision-making

Machine learning and health need better values

In medicine, how do we machine learn anything real?

Improving the Fairness of Chest X-ray Classifiers

Get To The Point! Problem-Based Curated Data Views To Augment Care For Critically Ill Patients

Counterfactually guided policy transfer in clinical settings

AI recognition of patient race in medical imaging: a modelling study

A comparison of approaches to improve worst-case predictive model performance over patient subpopulations

What every reader should know about studies using electronic health record data but may be afraid to ask

Visualization of deep models on nursing notes and physiological data for predicting health outcomes through temporal sliding windows

Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations

The role of machine learning in clinical research: transforming the future of evidence generation

The false hope of current approaches to explainable artificial intelligence in health care

Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

Reproducibility in machine learning for health research: Still a ways to go

Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing

Problems in the deployment of machine-learned models in health care

Predicting hospitalizations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study

Medical Dead-ends and Learning to Identify High-risk States and Treatments

Learning Optimal Predictive Checklists

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Implementing machine learning in medicine

Five principles for the intelligent use of AI in medical imaging

Equity in essence: a call for operationalising fairness in machine learning for healthcare

Do as AI say: susceptibility in deployment of clinical decision-aids

Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings

Characterizing generalization under out-of-distribution shifts in deep metric learning

Characteristics and outcomes of hospital admissions for COVID-19 and influenza in the Toronto area

Can You Fake It Until You Make It? Impacts of Differentially Private Synthetic Data on Downstream Classification Fairness

An empirical framework for domain generalization in clinical settings

Uniform Priors for Data-Efficient Transfer

Treating health disparities with artificial intelligence

Self-supervised contrastive learning of protein representations by mutual information maximization

S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning

Probabilistic machine learning for healthcare

Preparing a Clinical Support Model for Silent Mode in General Internal Medicine

Predicting covid-19 pneumonia severity on chest x-ray with deep learning

Patient characteristics, clinical care, resource use, and outcomes associated with hospitalization for COVID-19 in the Toronto area

Multiple sclerosis severity classification from clinical text

Mimic-extract: A data extraction, preprocessing, and representation pipeline for mimic-iii

Improving Dialogue Breakdown Detection with Semi-Supervised Learning

Hurtful words: quantifying biases in clinical contextual word embeddings

Ethical Machine Learning in Healthcare

Ensuring machine learning for healthcare works for all

Cross-Language Aphasia Detection using Optimal Transport Domain Adaptation

Covid-19 image data collection: Prospective predictions are the future

Confounding Feature Acquisition for Causal Effect Estimation

Chexpert++: Approximating the chexpert labeler for speed, differentiability, and probabilistic output

CheXclusion: Fairness gaps in deep chest X-ray classifiers

Challenges to the reproducibility of machine learning models in health care

Challenges of Differentially Private Prediction in Healthcare Settings

Building a data science platform for better health

An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare

A review of challenges and opportunities in machine learning for health

A comprehensive evaluation of multi-task learning and multi-task pre-training on EHR time-series data

Turning the crank for machine learning: ease, at what expense?

Towards characterizing the high-dimensional bias of kernel-based particle inference algorithms

The PLOS ONE collection on machine learning in health and biomedicine: Towards open code and open data

The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers

Reproducibility in machine learning for health

Practical guidance on artificial intelligence for health-care data

Modeling the biological pathology continuum with hsic-regularized wasserstein auto-encoders

Feature robustness in non-stationary health records: caveats to deployable model performance in common clinical machine learning tasks

Do no harm: a roadmap for responsible machine learning for health care

Clinically accurate chest x-ray report generation

Can AI help reduce disparities in general medical and mental health care?

Building a research partnership between computer scientists and health service researchers for access and analysis of population-level health datasets: what are we learning?

The effect of heterogeneous data for Alzheimer's disease detection from speech

Semi-supervised biomedical translation with cycle wasserstein regression GANs

Rethinking clinical prediction: why machine learning must consider year of care and feature aggregation

Racial disparities and mistrust in end-of-life care

Opportunities in machine learning for healthcare

Modeling mistrust in end-of-life care

Machine learning for health (ML4H) workshop at NeurIPS 2018

Clinicalvis: Supporting clinical task-focused design evaluation

Understanding vasopressor intervention and weaning: risk prediction in a public heterogeneous clinical time series database

The use of autoencoders for discovering patient phenotypes

Predicting intervention onset in the ICU with switching state space models

Learning Clinical Events

Deep reinforcement learning for sepsis treatment

Continuous state-space models for optimal sepsis treatment: a deep reinforcement learning approach

Clinical intervention prediction and understanding with deep neural networks

Uncovering voice misuse using symbolic mismatch

Sodium modelling to reduce intradialytic hypotension during haemodialysis for acute kidney injury in the intensive care unit

Prediction using patient comparison vs. modeling: A case study for mortality prediction

Predicting early psychiatric readmission with natural language processing of narrative discharge summaries

Data Analysis

State of the art review: the data revolution in critical care

Short-term mortality prediction for elderly patients using Medicare claims data

Metadata correction: making big data useful for health care: a summary of the inaugural mit critical data conference

A multivariate timeseries modeling approach to severity of illness assessment and forecasting in ICU with sparse, heterogeneous clinical data

Unfolding physiological state: Mortality modelling in intensive care units

Subglottal ambulatory monitoring of vocal function to improve voice disorder assessment

Making big data useful for health care: a summary of the inaugural mit critical data conference