Divya Shanmugam

Rajiv Movva, Divya Shanmugam, Kaihua Hou et al.

Healthcare data in the United States often records only a patient's coarse race group: for example, both Indian and Chinese patients are typically coded as "Asian." It is unknown, however, whether this coarse coding conceals meaningful disparities in the performance of clinical risk scores across granular race groups. Here we show that it does. Using data from 418K emergency department visits, we assess clinical risk score performance disparities across 26 granular groups for three outcomes, five risk scores, and four performance metrics. Across outcomes and metrics, we show that the risk scores exhibit significant granular performance disparities within coarse race groups. In fact, variation in performance within coarse groups often *exceeds* the variation between coarse groups. We explore why these disparities arise, finding that outcome rates, feature distributions, and the relationships between features and outcomes all vary significantly across granular groups. Our results suggest that healthcare providers, hospital systems, and machine learning researchers should strive to collect, release, and use granular race data in place of coarse race data, and that existing analyses may significantly underestimate racial disparities in performance.

Aniruddh Raghu, Divya Shanmugam, Eugene Pomerantsev et al.

Neural network models have demonstrated impressive performance in predicting pathologies and outcomes from the 12-lead electrocardiogram (ECG). However, these models often need to be trained with large, labelled datasets, which are not available for many predictive tasks of interest. In this work, we perform an empirical study examining whether training time data augmentation methods can be used to improve performance on such data-scarce ECG prediction problems. We investigate how data augmentation strategies impact model performance when detecting cardiac abnormalities from the ECG. Motivated by our finding that the effectiveness of existing augmentation strategies is highly task-dependent, we introduce a new method, TaskAug, which defines a flexible augmentation policy that is optimized on a per-task basis. We outline an efficient learning algorithm to do so that leverages recent work in nested optimization and implicit differentiation. In experiments, considering three datasets and eight predictive tasks, we find that TaskAug is competitive with or improves on prior work, and the learned policies shed light on what transformations are most effective for different tasks. We distill key insights from our experimental evaluation, generating a set of best practices for applying data augmentation to ECG prediction problems.

Helen Lu, Divya Shanmugam, Harini Suresh et al.

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models. Importantly, TTA can be used to improve model performance post-hoc, without additional training. Although test-time augmentation (TTA) can be applied to any data modality, it has seen limited adoption in NLP due in part to the difficulty of identifying label-preserving transformations. In this paper, we present augmentation policies that yield significant accuracy improvements with language models. A key finding is that augmentation policy design -- for instance, the number of samples generated from a single, non-deterministic augmentation -- has a considerable impact on the benefit of TTA. Experiments across a binary classification task and dataset show that test-time augmentation can deliver consistent improvements over current state-of-the-art approaches.

Erica Chiang, Divya Shanmugam, Ashley N. Beecy et al.

Disease progression models are widely used to inform the diagnosis and treatment of many progressive diseases. However, a significant limitation of existing models is that they do not account for health disparities that can bias the observed data. To address this, we develop an interpretable Bayesian disease progression model that captures three key health disparities: certain patient populations may (1) start receiving care only when their disease is more severe, (2) experience faster disease progression even while receiving care, or (3) receive follow-up care less frequently conditional on disease severity. We show theoretically and empirically that failing to account for any of these disparities can result in biased estimates of severity (e.g., underestimating severity for disadvantaged groups). On a dataset of heart failure patients, we show that our model can identify groups that face each type of health disparity, and that accounting for these disparities while inferring disease severity meaningfully shifts which patients are considered high-risk.

Divya Shanmugam, Monica Agrawal, Rajiv Movva et al.

The increased capabilities of generative AI have dramatically expanded its possible use cases in medicine. We provide a comprehensive overview of generative AI use cases for clinicians, patients, clinical trial organizers, researchers, and trainees. We then discuss the many challenges -- including maintaining privacy and security, improving transparency and interpretability, upholding equity, and rigorously evaluating models -- which must be overcome to realize this potential, and the open research directions they give rise to.

Divya Shanmugam, Shuvom Sadhuka, Manish Raghavan et al.

It remains difficult to evaluate machine learning classifiers in the absence of a large, labeled dataset. While labeled data can be prohibitively expensive or impossible to obtain, unlabeled data is plentiful. Here, we introduce Semi-Supervised Model Evaluation (SSME), a method that uses both labeled and unlabeled data to evaluate machine learning classifiers. SSME is the first evaluation method to take advantage of the fact that: (i) there are frequently multiple classifiers for the same task, (ii) continuous classifier scores are often available for all classes, and (iii) unlabeled data is often far more plentiful than labeled data. The key idea is to use a semi-supervised mixture model to estimate the joint distribution of ground truth labels and classifier predictions. We can then use this model to estimate any metric that is a function of classifier scores and ground truth labels (e.g., accuracy or expected calibration error). We present experiments in four domains where obtaining large labeled datasets is often impractical: (1) healthcare, (2) content moderation, (3) molecular property prediction, and (4) image annotation. Our results demonstrate that SSME estimates performance more accurately than do competing methods, reducing error by 5.1x relative to using labeled data alone and 2.4x relative to the next best competing method. SSME also improves accuracy when evaluating performance across subsets of the test distribution (e.g., specific demographic subgroups) and when evaluating the performance of language models.

Divya Shanmugam, Helen Lu, Swami Sankaranarayanan et al.

A conformal classifier produces a set of predicted classes and provides a probabilistic guarantee that the set includes the true class. Unfortunately, it is often the case that conformal classifiers produce uninformatively large sets. In this work, we show that test-time augmentation (TTA)--a technique that introduces inductive biases during inference--reduces the size of the sets produced by conformal classifiers. Our approach is flexible, computationally efficient, and effective. It can be combined with any conformal score, requires no model retraining, and reduces prediction set sizes by 10%-14% on average. We conduct an evaluation of the approach spanning three datasets, three models, two established conformal scoring methods, different guarantee strengths, and several distribution shifts to show when and why test-time augmentation is a useful addition to the conformal pipeline.

Divya Shanmugam, Kaihua Hou, Emma Pierson

Estimating the prevalence of a medical condition, or the proportion of the population in which it occurs, is a fundamental problem in healthcare and public health. Accurate estimates of the relative prevalence across groups -- capturing, for example, that a condition affects women more frequently than men -- facilitate effective and equitable health policy which prioritizes groups who are disproportionately affected by a condition. However, it is difficult to estimate relative prevalence when a medical condition is underreported. In this work, we provide a method for accurately estimating the relative prevalence of underreported medical conditions, building upon the positive unlabeled learning framework. We show that under the commonly made covariate shift assumption -- i.e., that the probability of having a disease conditional on symptoms remains constant across groups -- we can recover the relative prevalence, even without restrictive assumptions commonly made in positive unlabeled learning and even if it is impossible to recover the absolute prevalence. We conduct experiments on synthetic and real health data which demonstrate our method's ability to recover the relative prevalence more accurately than do baselines, and demonstrate the method's robustness to plausible violations of the covariate shift assumption. We conclude by illustrating the applicability of our method to case studies of intimate partner violence and hate speech.

Divya Shanmugam, Samira Shabanian, Fernando Diaz et al.

Modern machine learning systems are increasingly characterized by extensive personal data collection, despite the diminishing returns and increasing societal costs of such practices. Yet, data minimisation is one of the core data protection principles enshrined in the European Union's General Data Protection Regulation ('GDPR') and requires that only personal data that is adequate, relevant and limited to what is necessary is processed. However, the principle has seen limited adoption due to the lack of technical interpretation. In this work, we build on literature in machine learning and law to propose FIDO, a Framework for Inhibiting Data Overcollection. FIDO learns to limit data collection based on an interpretation of data minimization tied to system performance. Concretely, FIDO provides a data collection stopping criterion by iteratively updating an estimate of the performance curve, or the relationship between dataset size and performance, as data is acquired. FIDO estimates the performance curve via a piecewise power law technique that models distinct phases of an algorithm's performance throughout data collection separately. Empirical experiments show that the framework produces accurate performance curves and data collection stopping criteria across datasets and feature acquisition algorithms. We further demonstrate that many other families of curves systematically overestimate the return on additional data. Results and analysis from our investigation offer deeper insights into the relevant considerations when designing a data minimization framework, including the impacts of active feature acquisition on individual users and the feasability of user-specific data minimization. We conclude with practical recommendations for the implementation of data minimization.

Divya Shanmugam, Davis Blalock, Guha Balakrishnan et al.

Test-time augmentation -- the aggregation of predictions across transformed versions of a test input -- is a common practice in image classification. Traditionally, predictions are combined using a simple average. In this paper, we present 1) experimental analyses that shed light on cases in which the simple average is suboptimal and 2) a method to address these shortcomings. A key finding is that even when test-time augmentation produces a net improvement in accuracy, it can change many correct predictions into incorrect predictions. We delve into when and why test-time augmentation changes a prediction from being correct to incorrect and vice versa. Building on these insights, we present a learning-based method for aggregating test-time augmentations. Experiments across a diverse set of models, datasets, and augmentations show that our method delivers consistent improvements over existing approaches.

Roshni Sahoo, Divya Shanmugam, John Guttag

Current unsupervised domain adaptation methods can address many types of distribution shift, but they assume data from the source domain is freely available. As the use of pre-trained models becomes more prevalent, it is reasonable to assume that source data is unavailable. We propose an unsupervised method for adapting a source classifier to a target domain that varies from the source domain along natural axes, such as brightness and contrast. Our method only requires access to unlabeled target instances and the source classifier. We validate our method in scenarios where the distribution shift involves brightness, contrast, and rotation and show that it outperforms fine-tuning baselines in scenarios with limited labeled data.

Ava P. Soleimany, Harini Suresh, Jose Javier Gonzalez Ortiz et al.

Global eradication of malaria depends on the development of drugs effective against the silent, yet obligate liver stage of the disease. The gold standard in drug development remains microscopic imaging of liver stage parasites in in vitro cell culture models. Image analysis presents a major bottleneck in this pipeline since the parasite has significant variability in size, shape, and density in these models. As with other highly variable datasets, traditional segmentation models have poor generalizability as they rely on hand-crafted features; thus, manual annotation of liver stage malaria images remains standard. To address this need, we develop a convolutional neural network architecture that utilizes spatial dropout sampling for parasite segmentation and epistemic uncertainty estimation in images of liver stage malaria. Our pipeline produces high-precision segmentations nearly identical to expert annotations, generalizes well on a diverse dataset of liver stage malaria parasites, and promotes independence between learned feature maps to model the uncertainty of generated predictions.

Divya Shanmugam, Davis Blalock, John Guttag

Patients who suffer an acute coronary syndrome are at elevated risk for adverse cardiovascular events such as myocardial infarction and cardiovascular death. Accurate assessment of this risk is crucial to their course of care. We focus on estimating a patient's risk of cardiovascular death after an acute coronary syndrome based on a patient's raw electrocardiogram (ECG) signal. Learning from this signal is challenging for two reasons: 1) positive examples signifying a downstream cardiovascular event are scarce, causing drastic class imbalance, and 2) each patient's ECG signal consists of thousands of heartbeats, accompanied by a single label for the downstream outcome. Machine learning has been previously applied to this task, but most approaches rely on hand-crafted features and domain knowledge. We propose a method that learns a representation from the raw ECG signal by using a multiple instance learning framework. We present a learned risk score for cardiovascular death that outperforms existing risk metrics in predicting cardiovascular death within 30, 60, 90, and 365 days on a dataset of 5000 patients.