Andrew L. Beam

Benjamin Kompa, David R. Bellamy, Thomas Kolokotrones et al. · harvard

The No Unmeasured Confounding Assumption is widely used to identify causal effects in observational studies. Recent work on proximal inference has provided alternative identification results that succeed even in the presence of unobserved confounders, provided that one has measured a sufficiently rich set of proxy variables, satisfying specific structural conditions. However, proximal inference requires solving an ill-posed integral equation. Previous approaches have used a variety of machine learning techniques to estimate a solution to this integral equation, commonly referred to as the bridge function. However, prior work has often been limited by relying on pre-specified kernel functions, which are not data adaptive and struggle to scale to large datasets. In this work, we introduce a flexible and scalable method based on a deep neural network to estimate causal effects in the presence of unmeasured confounding using proximal inference. Our method achieves state of the art performance on two well-established proximal inference benchmarks. Finally, we provide theoretical consistency guarantees for our method.

Bhawesh Kumar, Anil Palepu, Rudraksh Tuwani et al. · deepmind

Self-supervised models trained with a contrastive loss such as CLIP have shown to be very powerful in zero-shot classification settings. However, to be used as a zero-shot classifier these models require the user to provide new captions over a fixed set of labels at test time. In many settings, it is hard or impossible to know if a new query caption is compatible with the source captions used to train the model. We address these limitations by framing the zero-shot classification task as an outlier detection problem and develop a conformal prediction procedure to assess when a given test caption may be reliably used. On a real-world medical example, we show that our proposed conformal procedure improves the reliability of CLIP-style models in the zero-shot classification setting, and we provide an empirical analysis of the factors that may affect its performance.

Joe B Hakim, Jeffery L Painter, Darmendra Ramcharran et al.

Large language models (LLMs) are useful tools with the capacity for performing specific types of knowledge work at an effective scale. However, LLM deployments in high-risk and safety-critical domains pose unique challenges, notably the issue of ``hallucination,'' where LLMs can generate fabricated information. This is particularly concerning in settings such as drug safety, where inaccuracies could lead to patient harm. To mitigate these risks, we have developed and demonstrated a proof of concept suite of guardrails specifically designed to mitigate certain types of hallucinations and errors for drug safety, and potentially applicable to other medical safety-critical contexts. These guardrails include mechanisms to detect anomalous documents to prevent the ingestion of inappropriate data, identify incorrect drug names or adverse event terms, and convey uncertainty in generated content. We integrated these guardrails with an LLM fine-tuned for a text-to-text task, which involves converting both structured and unstructured data within adverse event reports into natural language. This method was applied to translate individual case safety reports, demonstrating effective application in a pharmacovigilance processing task. Our guardrail framework offers a set of tools with broad applicability across various domains, ensuring LLMs can be safely used in high-risk situations by eliminating the occurrence of key errors, including the generation of incorrect pharmacovigilance-related terms, thus adhering to stringent regulatory and quality standards in medical safety-critical environments.

Anil Palepu, Andrew L. Beam

In this paper, we introduce a novel regularization scheme on contrastive language-image pre-trained (CLIP) medical vision models. Our approach is based on the observation that on many medical imaging tasks text tokens should only describe a small number of image regions and, likewise, each image region should correspond to only a few text tokens. In CLIP-style models, this implies that text-token embeddings should have high similarity to only a small number of image-patch embeddings for a given image-text pair. We formalize this observation using a novel regularization scheme that penalizes the entropy of the text-token to image-patch similarity scores. We qualitatively and quantitatively demonstrate that the proposed regularization scheme shrinks most of the pairwise text-token and image-patch similarity scores towards zero, thus achieving the desired effect. We demonstrate the promise of our approach in an important medical context, chest x-rays, where this underlying sparsity hypothesis naturally arises. Using our proposed approach, we achieve state of the art (SOTA) average zero-shot performance on the CheXpert and Padchest chest x-ray datasets, outperforming an unregularized version of the model and several recently published self-supervised models.

Anil Palepu, Andrew L Beam

Deep learning models trained in a fully supervised manner have been shown to rely on so-called "shortcut" features. Shortcut features are inputs that are associated with the outcome of interest in the training data, but are either no longer associated or not present in testing or deployment settings. Here we provide experiments that show recent self-supervised models trained on images and text provide more robust image representations and reduce the model's reliance on visual shortcut features on a realistic medical imaging example. Additionally, we find that these self-supervised models "forget" shortcut features more quickly than fully supervised ones when fine-tuned on labeled data. Though not a complete solution, our experiments provide compelling evidence that self-supervised models trained on images and text provide some resilience to visual shortcut features.

Yining Hua, Fenglin Liu, Kailai Yang et al.

Objectieve:This review aims to deliver a comprehensive analysis of Large Language Models (LLMs) utilization in mental health care, evaluating their effectiveness, identifying challenges, and exploring their potential for future application. Materials and Methods: A systematic search was performed across multiple databases including PubMed, Web of Science, Google Scholar, arXiv, medRxiv, and PsyArXiv in November 2023. The review includes all types of original research, regardless of peer-review status, published or disseminated between October 1, 2019, and December 2, 2023. Studies were included without language restrictions if they employed LLMs developed after T5 and directly investigated research questions within mental health care settings. Results: Out of an initial 313 articles, 34 were selected based on their relevance to LLMs applications in mental health care and the rigor of their reported outcomes. The review identified various LLMs applications in mental health care, including diagnostics, therapy, and enhancing patient engagement. Key challenges highlighted were related to data availability and reliability, the nuanced handling of mental states, and effective evaluation methods. While LLMs showed promise in improving accuracy and accessibility, significant gaps in clinical applicability and ethical considerations were noted. Conclusion: LLMs hold substantial promise for enhancing mental health care. For their full potential to be realized, emphasis must be placed on developing robust datasets, development and evaluation frameworks, ethical guidelines, and interdisciplinary collaborations to address current limitations.

Manqing Liu, David R. Bellamy, Andrew L. Beam

Causal inference is a critical task across fields such as healthcare, economics, and the social sciences. While recent advances in machine learning, especially those based on the deep-learning architectures, have shown potential in estimating causal effects, existing approaches often fall short in handling complex causal structures and lack adaptability across various causal scenarios. In this paper, we present a novel transformer-based method for causal inference that overcomes these challenges. The core innovation of our model lies in its integration of causal Directed Acyclic Graphs (DAGs) directly into the attention mechanism, enabling it to accurately model the underlying causal structure. This allows for flexible estimation of both average treatment effects (ATE) and conditional average treatment effects (CATE). Extensive experiments on both synthetic and real-world datasets demonstrate that our approach surpasses existing methods in estimating causal effects across a wide range of scenarios. The flexibility and robustness of our model make it a valuable tool for researchers and practitioners tackling complex causal inference problems.

David R. Bellamy, Bhawesh Kumar, Cindy Wang et al. · deepmind

In this work we introduce Labrador, a pre-trained Transformer model for laboratory data. Labrador and BERT were pre-trained on a corpus of 100 million lab test results from electronic health records (EHRs) and evaluated on various downstream outcome prediction tasks. Both models demonstrate mastery of the pre-training task but neither consistently outperform XGBoost on downstream supervised tasks. Our ablation studies reveal that transfer learning shows limited effectiveness for BERT and achieves marginal success with Labrador. We explore the reasons for the failure of transfer learning and suggest that the data generating process underlying each patient cannot be characterized sufficiently using labs alone, among other factors. We encourage future work to focus on joint modeling of multiple EHR data categories and to include tree-based baselines in their evaluations.

Manqing Liu, Andrew L. Beam

We present Doubly Robust Monte Carlo Tree Search (DR-MCTS), a novel algorithm that integrates Doubly Robust (DR) off-policy estimation into Monte Carlo Tree Search (MCTS) to enhance sample efficiency and decision quality in complex environments. Our approach introduces a hybrid estimator that combines MCTS rollouts with DR estimation, offering theoretical guarantees of unbiasedness and variance reduction under specified conditions. Empirical evaluations in Tic-Tac-Toe and the partially observable VirtualHome environment demonstrate DR-MCTS's superior performance over standard MCTS. In Tic-Tac-Toe, DR-MCTS achieves an 88% win rate compared to a 10% win rate for standard MCTS. In compound VirtualHome tasks, DR-MCTS attains a 20.7% success rate versus 10.3% for standard MCTS. Our scaling analysis reveals that DR-MCTS exhibits better sample efficiency, notably outperforming standard MCTS with larger language models while using a smaller model. These results underscore DR-MCTS's potential for efficient decision-making in complex, real-world scenarios where sample efficiency is paramount.

Sophia M Rein, Jing Li, Miguel Hernan et al.

The g-formula can be used to estimate causal effects of sustained treatment strategies using observational data under the identifying assumptions of consistency, positivity, and exchangeability. The non-iterative conditional expectation (NICE) estimator of the g-formula also requires correct estimation of the conditional distribution of the time-varying treatment, confounders, and outcome. Parametric models, which have been traditionally used for this purpose, are subject to model misspecification, which may result in biased causal estimates. Here, we propose a unified deep learning framework for the NICE g-formula estimator that uses multitask recurrent neural networks for estimation of the joint conditional distributions. Using simulated data, we evaluated our model's bias and compared it with that of the parametric g-formula estimator. We found lower bias in the estimates of the causal effect of sustained treatment strategies on a survival outcome when using the deep learning estimator compared with the parametric NICE estimator in settings with simple and complex temporal dependencies between covariates. These findings suggest that our Deep Learning g-formula estimator may be less sensitive to model misspecification than the classical parametric NICE estimator when estimating the causal effect of sustained treatment strategies from complex observational data.

Bhawesh Kumar, Charlie Lu, Gauri Gupta et al.

As large language models continue to be widely developed, robust uncertainty quantification techniques will become crucial for their safe deployment in high-stakes scenarios. In this work, we explore how conformal prediction can be used to provide uncertainty quantification in language models for the specific task of multiple-choice question-answering. We find that the uncertainty estimates from conformal prediction are tightly correlated with prediction accuracy. This observation can be useful for downstream applications such as selective classification and filtering out low-quality predictions. We also investigate the exchangeability assumption required by conformal prediction to out-of-subject questions, which may be a more realistic scenario for many practical applications. Our work contributes towards more trustworthy and reliable usage of large language models in safety-critical situations, where robust guarantees of error rate are required.

Akshay Smit, Damir Vrabac, Yujie He et al.

We propose a selective learning method using meta-learning and deep reinforcement learning for medical image interpretation in the setting of limited labeling resources. Our method, MedSelect, consists of a trainable deep learning selector that uses image embeddings obtained from contrastive pretraining for determining which images to label, and a non-parametric selector that uses cosine similarity to classify unseen images. We demonstrate that MedSelect learns an effective selection strategy outperforming baseline selection strategies across seen and unseen medical conditions for chest X-ray interpretation. We also perform an analysis of the selections performed by MedSelect comparing the distribution of latent embeddings and clinical features, and find significant differences compared to the strongest performing baseline. We believe that our method may be broadly applicable across medical imaging settings where labels are expensive to acquire.

Allen Schmaltz, Andrew Beam

We present a novel end-to-end language model for joint retrieval and classification, unifying the strengths of bi- and cross- encoders into a single language model via a coarse-to-fine memory matching search procedure for learning and inference. Evaluated on the standard blind test set of the FEVER fact verification dataset, classification accuracy is significantly higher than approaches that only rely on the language model parameters as a knowledge base, and approaches some recent multi-model pipeline systems, using only a single BERT base model augmented with memory layers. We further demonstrate how coupled retrieval and classification can be leveraged to identify low confidence instances, and we extend exemplar auditing to this setting for analyzing and constraining the model. As a result, our approach yields a means of updating language model behavior through two distinct mechanisms: The retrieved information can be updated explicitly, and the model behavior can be modified via the exemplar database.

David Bellamy, Leo Celi, Andrew L. Beam

The Large Scale Visual Recognition Challenge based on the well-known Imagenet dataset catalyzed an intense flurry of progress in computer vision. Benchmark tasks have propelled other sub-fields of machine learning forward at an equally impressive pace, but in healthcare it has primarily been image processing tasks, such as in dermatology and radiology, that have experienced similar benchmark-driven progress. In the present study, we performed a comprehensive review of benchmarks in medical machine learning for structured data, identifying one based on the Medical Information Mart for Intensive Care (MIMIC-III) that allows the first direct comparison of predictive performance and thus the evaluation of progress on four clinical prediction tasks: mortality, length of stay, phenotyping, and patient decompensation. We find that little meaningful progress has been made over a 3 year period on these tasks, despite significant community engagement. Through our meta-analysis, we find that the performance of deep recurrent models is only superior to logistic regression on certain tasks. We conclude with a synthesis of these results, possible explanations, and a list of desirable qualities for future benchmarks in medical machine learning.

Allen Schmaltz, Andrew Beam

Many practical applications of AI in medicine consist of semi-supervised discovery: The investigator aims to identify features of interest at a resolution more fine-grained than that of the available human labels. This is often the scenario faced in healthcare applications as coarse, high-level labels (e.g., billing codes) are often the only sources that are readily available. These challenges are compounded for modalities such as text, where the feature space is very high-dimensional, and often contains considerable amounts of noise. In this work, we generalize a recently proposed zero-shot sequence labeling method, "binary labeling via a convolutional decomposition", to the case where the available document-level human labels are themselves relatively high-dimensional. The approach yields classification with "introspection", relating the fine-grained features of an inference-time prediction to their nearest neighbors from the training set, under the model. The approach is effective, yet parsimonious, as demonstrated on a well-studied MIMIC-III multi-label classification task of electronic health record data, and is useful as a tool for organizing the analysis of neural model predictions and high-dimensional datasets. Our proposed approach yields both a competitively effective classification model and an interrogation mechanism to aid healthcare workers in understanding the salient features that drive the model's predictions.

Natalia Antropova, Andrew L. Beam, Brett K. Beaulieu-Jones et al.

This volume represents the accepted submissions from the Machine Learning for Health (ML4H) workshop at the conference on Neural Information Processing Systems (NeurIPS) 2018, held on December 8, 2018 in Montreal, Canada.

Brett K. Beaulieu-Jones, Isaac S. Kohane, Andrew L. Beam

Biomedical association studies are increasingly done using clinical concepts, and in particular diagnostic codes from clinical data repositories as phenotypes. Clinical concepts can be represented in a meaningful, vector space using word embedding models. These embeddings allow for comparison between clinical concepts or for straightforward input to machine learning models. Using traditional approaches, good representations require high dimensionality, making downstream tasks such as visualization more difficult. We applied Poincaré embeddings in a 2-dimensional hyperbolic space to a large-scale administrative claims database and show performance comparable to 100-dimensional embeddings in a euclidean space. We then examine disease relationships under different disease contexts to better understand potential phenotypes.

Marzyeh Ghassemi, Tristan Naumann, Peter Schulam et al.

Modern electronic health records (EHRs) provide data to answer clinically meaningful questions. The growing data in EHRs makes healthcare ripe for the use of machine learning. However, learning in a clinical setting presents unique challenges that complicate the use of common machine learning methodologies. For example, diseases in EHRs are poorly labeled, conditions can encompass multiple underlying endotypes, and healthy individuals are underrepresented. This article serves as a primer to illuminate these challenges and highlights opportunities for members of the machine learning community to contribute to healthcare.

Samuel G. Finlayson, Hyung Won Chung, Isaac S. Kohane et al.

The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we demonstrate that adversarial examples are capable of manipulating deep learning systems across three clinical domains. For each of our representative medical deep learning classifiers, both white and black box attacks were highly successful. Our models are representative of the current state of the art in medical computer vision and, in some cases, directly reflect architectures already seeing deployment in real world clinical settings. In addition to the technical contribution of our paper, we synthesize a large body of knowledge about the healthcare system to argue that medicine may be uniquely susceptible to adversarial attacks, both in terms of monetary incentives and technical vulnerability. To this end, we outline the healthcare economy and the incentives it creates for fraud and provide concrete examples of how and why such attacks could be realistically carried out. We urge practitioners to be aware of current vulnerabilities when deploying deep learning systems in clinical settings, and encourage the machine learning community to further investigate the domain-specific characteristics of medical learning systems.

Andrew L. Beam, Benjamin Kompa, Allen Schmaltz et al.

Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing. In this article, we present a new set of embeddings for medical concepts learned using an extremely large collection of multimodal medical data. Leaning on recent theoretical insights, we demonstrate how an insurance claims database of 60 million members, a collection of 20 million clinical notes, and 1.7 million full text biomedical journal articles can be combined to embed concepts into a common space, resulting in the largest ever set of embeddings for 108,477 medical concepts. To evaluate our approach, we present a new benchmark methodology based on statistical power specifically designed to test embeddings of medical concepts. Our approach, called cui2vec, attains state-of-the-art performance relative to previous methods in most instances. Finally, we provide a downloadable set of pre-trained embeddings for other researchers to use, as well as an online tool for interactive exploration of the cui2vec embeddings

Andrew L. Beam, Alison Motsinger-Reif, Jon Doyle

Discovering causal genetic variants from large genetic association studies poses many difficult challenges. Assessing which genetic markers are involved in determining trait status is a computationally demanding task, especially in the presence of gene-gene interactions. A non-parametric Bayesian approach in the form of a Bayesian neural network is proposed for use in analyzing genetic association studies. Demonstrations on synthetic and real data reveal they are able to efficiently and accurately determine which variants are involved in determining case-control status. Using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude. In comparison with commonly used approaches for detecting genetic interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships while having the computational efficiency needed to handle large datasets.