FoMoH: A clinically meaningful foundation model evaluation for structured electronic health records

Foundation models hold significant promise in healthcare, given their capacity to extract meaningful representations independent of downstream tasks. This property has enabled state-of-the-art performance across several clinical applications trained on structured electronic health record (EHR) data, even in settings with limited labeled data, a prevalent challenge in healthcare. However, there is little consensus on these models' potential for clinical utility due to the lack of desiderata of comprehensive and meaningful tasks and sufficiently diverse evaluations to characterize the benefit over conventional supervised learning. To address this gap, we propose a suite of clinically meaningful tasks spanning patient outcomes, early prediction of acute and chronic conditions, including desiderata for robust evaluations. We evaluate state-of-the-art foundation models on EHR data consisting of 5 million patients from Columbia University Irving Medical Center (CUMC), a large urban academic medical center in New York City, across 14 clinically relevant tasks. We measure overall accuracy, calibration, and subpopulation performance to surface tradeoffs based on the choice of pre-training, tokenization, and data representation strategies. Our study aims to advance the empirical evaluation of structured EHR foundation models and guide the development of future healthcare foundation models.

ICYM2I: The illusion of multimodal informativeness under missingness

Multimodal learning is of continued interest in artificial intelligence-based applications, motivated by the potential information gain from combining different types of data. However, modalities collected and curated during development may differ from the modalities available at deployment due to multiple factors including cost, hardware failure, or -- as we argue in this work -- the perceived informativeness of a given modality. Na{\"i}ve estimation of the information gain associated with including an additional modality without accounting for missingness may result in improper estimates of that modality's value in downstream tasks. Our work formalizes the problem of missingness in multimodal learning and demonstrates the biases resulting from ignoring this process. To address this issue, we introduce ICYM2I (In Case You Multimodal Missed It), a framework for the evaluation of predictive performance and information gain under missingness through inverse probability weighting-based correction. We demonstrate the importance of the proposed adjustment to estimate information gain under missingness on synthetic, semi-synthetic, and real-world medical datasets.

A Planning Framework for Adaptive Labeling

Ground truth labels/outcomes are critical for advancing scientific and engineering applications, e.g., evaluating the treatment effect of an intervention or performance of a predictive model. Since randomly sampling inputs for labeling can be prohibitively expensive, we introduce an adaptive labeling framework where measurement effort can be reallocated in batches. We formulate this problem as a Markov decision process where posterior beliefs evolve over time as batches of labels are collected (state transition), and batches (actions) are chosen to minimize uncertainty at the end of data collection. We design a computational framework that is agnostic to different uncertainty quantification approaches including those based on deep learning, and allows a diverse array of policy gradient approaches by relying on continuous policy parameterizations. On real and synthetic datasets, we demonstrate even a one-step lookahead policy can substantially outperform common adaptive labeling heuristics, highlighting the virtue of planning. On the methodological side, we note that standard REINFORCE-style policy gradient estimators can suffer high variance since they rely only on zeroth order information. We propose a direct backpropagation-based approach, Smoothed-Autodiff, based on a carefully smoothed version of the original non-differentiable MDP. Our method enjoys low variance at the price of introducing bias, and we theoretically and empirically show that this trade-off can be favorable.

Machine Learning for Health symposium 2022 -- Extended Abstract track

A collection of the extended abstracts that were presented at the 2nd Machine Learning for Health symposium (ML4H 2022), which was held both virtually and in person on November 28, 2022, in New Orleans, Louisiana, USA. Machine Learning for Health (ML4H) is a longstanding venue for research into machine learning for health, including both theoretical works and applied works. ML4H 2022 featured two submission tracks: a proceedings track, which encompassed full-length submissions of technically mature and rigorous work, and an extended abstract track, which would accept less mature, but innovative research for discussion. All the manuscripts submitted to ML4H Symposium underwent a double-blind peer-review process. Extended abstracts included in this collection describe innovative machine learning research focused on relevant problems in health and biomedicine.

"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts

Performance of machine learning models may differ between training and deployment for many reasons. For instance, model performance can change between environments due to changes in data quality, observing a different population than the one in training, or changes in the relationship between labels and features. These manifest as changes to the underlying data generating mechanisms, and thereby result in distribution shifts across environments. Attributing performance changes to specific shifts, such as covariate or concept shifts, is critical for identifying sources of model failures, and for taking mitigating actions that ensure robust models. In this work, we introduce the problem of attributing performance differences between environments to shifts in the underlying data generating mechanisms. We formulate the problem as a cooperative game and derive an importance weighting method for computing the value of a coalition (or a set) of distributions. The contribution of each distribution to the total performance change is then quantified as its Shapley value. We demonstrate the correctness and utility of our method on two synthetic datasets and two real-world case studies, showing its effectiveness in attributing performance changes to a wide range of distribution shifts.

Towards Robust Off-Policy Evaluation via Human Inputs

Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to undergo changes (that is, dataset shifts), it is important for OPE methods to perform robust evaluation of the policies amidst such changes. Existing approaches consider robustness against a large class of shifts that can arbitrarily change any observable property of the environment. This often results in highly pessimistic estimates of the utilities, thereby invalidating policies that might have been useful in deployment. In this work, we address the aforementioned problem by investigating how domain knowledge can help provide more realistic estimates of the utilities of policies. We leverage human inputs on which aspects of the environments may plausibly change, and adapt the OPE methods to only consider shifts on these aspects. Specifically, we propose a novel framework, Robust OPE (ROPE), which considers shifts on a subset of covariates in the data based on user inputs, and estimates worst-case utility under these shifts. We then develop computationally efficient algorithms for OPE that are robust to the aforementioned shifts for contextual bandits and Markov decision processes. We also theoretically analyze the sample complexity of these algorithms. Extensive experimentation with synthetic and real world datasets from the healthcare domain demonstrates that our approach not only captures realistic dataset shifts accurately, but also results in less pessimistic policy evaluations.

Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making

Assessing the effects of a policy based on observational data from a different policy is a common problem across several high-stake decision-making domains, and several off-policy evaluation (OPE) techniques have been proposed. However, these methods largely formulate OPE as a problem disassociated from the process used to generate the data (i.e. structural assumptions in the form of a causal graph). We argue that explicitly highlighting this association has important implications on our understanding of the fundamental limits of OPE. First, this implies that current formulation of OPE corresponds to a narrow set of tasks, i.e. a specific causal estimand which is focused on prospective evaluation of policies over populations or sub-populations. Second, we demonstrate how this association motivates natural desiderata to consider a general set of causal estimands, particularly extending the role of OPE for counterfactual off-policy evaluation at the level of individuals of the population. A precise description of the causal estimand highlights which OPE estimands are identifiable from observational data under the stated generative assumptions. For those OPE estimands that are not identifiable, the causal perspective further highlights where more experimental data is necessary, and highlights situations where human expertise can aid identification and estimation. Furthermore, many formalisms of OPE overlook the role of uncertainty entirely in the estimation process.We demonstrate how specifically characterising the causal estimand highlights the different sources of uncertainty and when human expertise can naturally manage this uncertainty. We discuss each of these aspects as actionable desiderata for future OPE research at scale and in-line with practical utility.

Pre-emptive learning-to-defer for sequential medical decision-making under uncertainty

We propose SLTD (`Sequential Learning-to-Defer') a framework for learning-to-defer pre-emptively to an expert in sequential decision-making settings. SLTD measures the likelihood of improving value of deferring now versus later based on the underlying uncertainty in dynamics. In particular, we focus on the non-stationarity in the dynamics to accurately learn the deferral policy. We demonstrate our pre-emptive deferral can identify regions where the current policy has a low probability of improving outcomes. SLTD outperforms existing non-sequential learning-to-defer baselines, whilst reducing overall uncertainty on multiple synthetic and real-world simulators with non-stationary dynamics. We further derive and decompose the propagated (long-term) uncertainty for interpretation by the domain expert to provide an indication of when the model's performance is reliable.

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

Machine learning models achieve state-of-the-art performance on many supervised learning tasks. However, prior evidence suggests that these models may learn to rely on shortcut biases or spurious correlations (intuitively, correlations that do not hold in the test as they hold in train) for good predictive performance. Such models cannot be trusted in deployment environments to provide accurate predictions. While viewing the problem from a causal lens is known to be useful, the seamless integration of causation techniques into machine learning pipelines remains cumbersome and expensive. In this work, we study and extend a causal pre-training debiasing technique called causal bootstrapping (CB) under five practical confounded-data generation-acquisition scenarios (with known and unknown confounding). Under these settings, we systematically investigate the effect of confounding bias on deep learning model performance, demonstrating their propensity to rely on shortcut biases when these biases are not properly accounted for. We demonstrate that such a causal pre-training technique can significantly outperform existing base practices to mitigate confounding bias on real-world domain generalization benchmarking tasks. This systematic investigation underlines the importance of accounting for the underlying data-generating mechanisms and fortifying data-preprocessing pipelines with a causal framework to develop methods robust to confounding biases.

On the Connections between Counterfactual Explanations and Adversarial Examples

Counterfactual explanations and adversarial examples have emerged as critical research areas for addressing the explainability and robustness goals of machine learning (ML). While counterfactual explanations were developed with the goal of providing recourse to individuals adversely impacted by algorithmic decisions, adversarial examples were designed to expose the vulnerabilities of ML models. While prior research has hinted at the commonalities between these frameworks, there has been little to no work on systematically exploring the connections between the literature on counterfactual explanations and adversarial examples. In this work, we make one of the first attempts at formalizing the connections between counterfactual explanations and adversarial examples. More specifically, we theoretically analyze salient counterfactual explanation and adversarial example generation methods, and highlight the conditions under which they behave similarly. Our analysis demonstrates that several popular counterfactual explanation and adversarial example generation methods such as the ones proposed by Wachter et. al. and Carlini and Wagner (with mean squared error loss), and C-CHVAE and natural adversarial examples by Zhao et. al. are equivalent. We also bound the distance between counterfactual explanations and adversarial examples generated by Wachter et. al. and DeepFool methods for linear models. Finally, we empirically validate our theoretical findings using extensive experimentation with synthetic and real world datasets.