arXiv subjects

Cynthia Rudin

Publications and source records attributed to Cynthia Rudin.

At least 73 records · Page 4Linked to original sources

arXiv2023

Reconsideration on evaluation of machine learning models in continuous monitoring using wearables

This paper explores the challenges in evaluating machine learning (ML) models for continuous health monitoring using wearable devices beyond conventional metrics. We state the complexities posed by real-world variability, disease dynamics, user-specific characteristics, and the prevalence of false notifications, necessitating novel evaluation strategies. Drawing insights from large-scale heart studies, the paper offers a comprehensive guideline for robust ML model evaluation on continuous health monitoring.

cs.LG↗

arXiv2023

ProtoEEGNet: An Interpretable Approach for Detecting Interictal Epileptiform Discharges

In electroencephalogram (EEG) recordings, the presence of interictal epileptiform discharges (IEDs) serves as a critical biomarker for seizures or seizure-like events.Detecting IEDs can be difficult; even highly trained experts disagree on the same sample. As a result, specialists have turned to machine-learning models for assistance. However, many existing models are black boxes and do not provide any human-interpretable reasoning for their decisions. In high-stakes medical applications, it is critical to have interpretable models so that experts can validate the reasoning of the model before making important diagnoses. We introduce ProtoEEGNet, a model that achieves state-of-the-art accuracy for IED detection while additionally providing an interpretable justification for its classifications. Specifically, it can reason that one EEG looks similar to another ''prototypical'' EEG that is known to contain an IED. ProtoEEGNet can therefore help medical professionals effectively detect IEDs while maintaining a transparent decision-making process.

eess.SP↗

arXiv2023

Exploring and Interacting with the Set of Good Sparse Generalized Additive Models

In real applications, interaction between machine learning models and domain experts is critical; however, the classical machine learning paradigm that usually produces only a single model does not facilitate such interaction. Approximating and exploring the Rashomon set, i.e., the set of all near-optimal models, addresses this practical challenge by providing the user with a searchable space containing a diverse set of models from which domain experts can choose. We present algorithms to efficiently and accurately approximate the Rashomon set of sparse, generalized additive models with ellipsoids for fixed support sets and use these ellipsoids to approximate Rashomon sets for many different support sets. The approximated Rashomon set serves as a cornerstone to solve practical challenges such as (1) studying the variable importance for the model class; (2) finding models under user-specified constraints (monotonicity, direct editing); and (3) investigating sudden changes in the shape functions. Experiments demonstrate the fidelity of the approximated Rashomon set and its effectiveness in solving practical challenges.

cs.LG↗

arXiv2023

Sparse Density Trees and Lists: An Interpretable Alternative to High-Dimensional Histograms

We present sparse tree-based and list-based density estimation methods for binary/categorical data. Our density estimation models are higher dimensional analogies to variable bin width histograms. In each leaf of the tree (or list), the density is constant, similar to the flat density within the bin of a histogram. Histograms, however, cannot easily be visualized in more than two dimensions, whereas our models can. The accuracy of histograms fades as dimensions increase, whereas our models have priors that help with generalization. Our models are sparse, unlike high-dimensional fixed-bin histograms. We present three generative modeling methods, where the first one allows the user to specify the preferred number of leaves in the tree within a Bayesian prior. The second method allows the user to specify the preferred number of branches within the prior. The third method returns density lists (rather than trees) and allows the user to specify the preferred number of rules and the length of rules within the prior. The new approaches often yield a better balance between sparsity and accuracy of density estimates than other methods for this task. We present an application to crime analysis, where we estimate how unusual each type of modus operandi is for a house break-in.

stat.ML↗

arXiv2023

Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection using Eight Million Samples Labeled with Imprecise Arrhythmia Alarms

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, further advancement of this paradigm of continuous AF detection in ambulatory settings, towards a population-wide screening use case, still faces several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, in this study, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5M 30-second records from 24100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in multiple aspects including handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.

eess.SP↗

arXiv2023

A Path to Simpler Models Starts With Noise

The Rashomon set is the set of models that perform approximately equally well on a given dataset, and the Rashomon ratio is the fraction of all models in a given hypothesis space that are in the Rashomon set. Rashomon ratios are often large for tabular datasets in criminal justice, healthcare, lending, education, and in other areas, which has practical implications about whether simpler models can attain the same level of accuracy as more complex models. An open question is why Rashomon ratios often tend to be large. In this work, we propose and study a mechanism of the data generation process, coupled with choices usually made by the analyst during the learning process, that determines the size of the Rashomon ratio. Specifically, we demonstrate that noisier datasets lead to larger Rashomon ratios through the way that practitioners train models. Additionally, we introduce a measure called pattern diversity, which captures the average difference in predictions between distinct classification patterns in the Rashomon set, and motivate why it tends to increase with label noise. Our results explain a key aspect of why simpler models often tend to perform as well as black box models on complex, noisier datasets.

cs.LG↗

arXiv2023

This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations

We present ProtoConcepts, a method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts. Existing work in prototype-based image classification uses a ``this looks like that'' reasoning process, which dissects a test image by finding prototypical parts and combining evidence from these prototypes to make a final classification. However, all of the existing prototypical part-based image classifiers provide only one-to-one comparisons, where a single training image patch serves as a prototype to compare with a part of our test image. With these single-image comparisons, it can often be difficult to identify the underlying concept being compared (e.g., ``is it comparing the color or the shape?''). Our proposed method modifies the architecture of prototype-based networks to instead learn prototypical concepts which are visualized using multiple image patches. Having multiple visualizations of the same prototype allows us to more easily identify the concept captured by that prototype (e.g., ``the test image and the related training patches are all the same shade of blue''), and allows our model to create richer, more interpretable visual explanations. Our experiments show that our ``this looks like those'' reasoning process can be applied as a modification to a wide range of existing prototypical image classification networks while achieving comparable accuracy on benchmark datasets.

cs.CV↗

arXiv2023

Uncertainty Quantification of Bandgaps in Acoustic Metamaterials with Stochastic Geometric Defects and Material Properties

This paper studies the utility of techniques within uncertainty quantification, namely spectral projection and polynomial chaos expansion, in reducing sampling needs for characterizing acoustic metamaterial dispersion band responses given stochastic material properties and geometric defects. A novel method of encoding geometric defects in an interpretable, resolution independent is showcased in the formation of input space probability distributions. Orders of magnitude sampling reductions down to $\sim10^0$ and $\sim10^1$ are achieved in the 1D and 7D input space scenarios respectively while maintaining accurate output space probability distributions through combining Monte Carlo, quadrature rule, and sparse grid sampling with surrogate model fitting.

cs.SD↗

arXiv2023

Optimal Sparse Decision Trees

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980's. The problem that has plagued decision tree algorithms since their inception is their lack of optimality, or lack of guarantees of closeness to optimality: decision tree algorithms are often greedy or myopic, and sometimes produce unquestionably suboptimal models. Hardness of decision tree optimization is both a theoretical and practical obstacle, and even careful mathematical programming approaches have not been able to solve these problems efficiently. This work introduces the first practical algorithm for optimal decision trees for binary variables. The algorithm is a co-design of analytical bounds that reduce the search space and modern systems techniques, including data structures and a custom bit-vector library. Our experiments highlight advantages in scalability, speed, and proof of optimality. The code is available at https://github.com/xiyanghu/OSDT.

cs.LG↗

arXiv2023

A Self-Supervised Algorithm for Denoising Photoplethysmography Signals for Heart Rate Estimation from Wearables

Smart watches and other wearable devices are equipped with photoplethysmography (PPG) sensors for monitoring heart rate and other aspects of cardiovascular health. However, PPG signals collected from such devices are susceptible to corruption from noise and motion artifacts, which cause errors in heart rate estimation. Typical denoising approaches filter or reconstruct the signal in ways that eliminate much of the morphological information, even from the clean parts of the signal that would be useful to preserve. In this work, we develop an algorithm for denoising PPG signals that reconstructs the corrupted parts of the signal, while preserving the clean parts of the PPG signal. Our novel framework relies on self-supervised training, where we leverage a large database of clean PPG signals to train a denoising autoencoder. As we show, our reconstructed signals provide better estimates of heart rate from PPG signals than the leading heart rate estimation methods. Further experiments show significant improvement in Heart Rate Variability (HRV) estimation from PPG signals using our algorithm. We conclude that our algorithm denoises PPG signals in a way that can improve downstream analysis of many different health metrics from wearable devices.

eess.SP↗

arXiv2023

Variable Importance Matching for Causal Inference

Our goal is to produce methods for observational causal inference that are auditable, easy to troubleshoot, accurate for treatment effect estimation, and scalable to high-dimensional data. We describe a general framework called Model-to-Match that achieves these goals by (i) learning a distance metric via outcome modeling, (ii) creating matched groups using the distance metric, and (iii) using the matched groups to estimate treatment effects. Model-to-Match uses variable importance measurements to construct a distance metric, making it a flexible framework that can be adapted to various applications. Concentrating on the scalability of the problem in the number of potential confounders, we operationalize the Model-to-Match framework with LASSO. We derive performance guarantees for settings where LASSO outcome modeling consistently identifies all confounders (importantly without requiring the linear model to be correctly specified). We also provide experimental results demonstrating the method's auditability, accuracy, and scalability as well as extensions to more general nonparametric outcome modeling.

stat.ME↗

arXiv2023

MALTS: Matching After Learning to Stretch

We introduce a flexible framework that produces high-quality almost-exact matches for causal inference. Most prior work in matching uses ad-hoc distance metrics, often leading to poor quality matches, particularly when there are irrelevant covariates. In this work, we learn an interpretable distance metric for matching, which leads to substantially higher quality matches. The learned distance metric stretches the covariate space according to each covariate's contribution to outcome prediction: this stretching means that mismatches on important covariates carry a larger penalty than mismatches on irrelevant covariates. Our ability to learn flexible distance metrics leads to matches that are interpretable and useful for the estimation of conditional average treatment effects.

stat.ME↗

arXiv2023

Missing Values and Imputation in Healthcare Data: Can Interpretable Machine Learning Help?

Missing values are a fundamental problem in data science. Many datasets have missing values that must be properly handled because the way missing values are treated can have large impact on the resulting machine learning model. In medical applications, the consequences may affect healthcare decisions. There are many methods in the literature for dealing with missing values, including state-of-the-art methods which often depend on black-box models for imputation. In this work, we show how recent advances in interpretable machine learning provide a new perspective for understanding and tackling the missing value problem. We propose methods based on high-accuracy glass-box Explainable Boosting Machines (EBMs) that can help users (1) gain new insights on missingness mechanisms and better understand the causes of missingness, and (2) detect -- or even alleviate -- potential risks introduced by imputation algorithms. Experiments on real-world medical datasets illustrate the effectiveness of the proposed methods.

cs.LG↗

arXiv2023

Optimal Sparse Regression Trees

Regression trees are one of the oldest forms of AI models, and their predictions can be made without a calculator, which makes them broadly useful, particularly for high-stakes applications. Within the large literature on regression trees, there has been little effort towards full provable optimization, mainly due to the computational hardness of the problem. This work proposes a dynamic-programming-with-bounds approach to the construction of provably-optimal sparse regression trees. We leverage a novel lower bound based on an optimal solution to the k-Means clustering algorithm in 1-dimension over the set of labels. We are often able to find optimal sparse trees in seconds, even for challenging datasets that involve large numbers of samples and highly-correlated features.

cs.LG↗

arXiv2023

Matched Machine Learning: A Generalized Framework for Treatment Effect Inference With Learned Metrics

We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching, a longstanding tool in observational causal inference. Interpretability is paramount in many high-stakes application of causal inference. Current tools for nonparametric estimation of both average and individualized treatment effects are black-boxes that do not allow for human auditing of estimates. Our framework uses machine learning to learn an optimal metric for matching units and estimating outcomes, thus achieving the performance of machine learning black-boxes, while being interpretable. Our general framework encompasses several published works as special cases. We provide asymptotic inference theory for our proposed framework, enabling users to construct approximate confidence intervals around estimates of both individualized and average treatment effects. We show empirically that instances of Matched Machine Learning perform on par with black-box machine learning methods and better than existing matching methods for similar problems. Finally, in our application we show how Matched Machine Learning can be used to perform causal inference even when covariate data are highly complex: we study an image dataset, and produce high quality matches and estimates of treatment effects.

stat.ME↗

arXiv2023

dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference

dame-flame is a Python package for performing matching for observational causal inference on datasets containing discrete covariates. This package implements the Dynamic Almost Matching Exactly (DAME) and Fast Large-Scale Almost Matching Exactly (FLAME) algorithms, which match treatment and control units on subsets of the covariates. The resulting matched groups are interpretable, because the matches are made on covariates, and high-quality, because machine learning is used to determine which covariates are important to match on. DAME solves an optimization problem that matches units on as many covariates as possible, prioritizing matches on important covariates. FLAME approximates the solution found by DAME via a much faster backward feature selection procedure. The package provides several adjustable parameters to adapt the algorithms to specific applications, and can calculate treatment effect estimates after matching. Descriptions of these parameters, details on estimating treatment effects, and further examples, can be found in the documentation at https://almost-matching-exactly.github.io/DAME-FLAME-Python-Package/

cs.LG↗

arXiv2023

Matching Bounds: How Choice of Matching Algorithm Impacts Treatment Effects Estimates and What to Do about It

Many major works in social science employ matching to make causal conclusions, but different matches on the same data may produce different treatment effect estimates, even when they achieve similar balance or minimize the same loss function. We discuss reasons and consequences of this problem. We present evidence of this problem by replicating ten papers that use matching and we find that different popular matching algorithms produce inconsistent results. We introduce Matching Bounds: a finite-sample, nonstochastic method that allows analysts to know whether a matched sample that produces different results with the same levels of balance and overall match quality could be obtained from their data. We apply Matching Bounds to a replication of two studies and show that in one case results are robust to this issue and in another they are not.

stat.AP↗

arXiv2023

Effects of Epileptiform Activity on Discharge Outcome in Critically Ill Patients

Epileptiform activity (EA) is associated with worse outcomes including increased risk of disability and death. However, the effect of EA on the neurologic outcome is confounded by the feedback between treatment with anti-seizure medications (ASM) and EA burden. A randomized clinical trial is challenging due to the sequential nature of EA-ASM feedback, as well as ethical reasons. However, some mechanistic knowledge is available, e.g., how drugs are absorbed. This knowledge together with observational data could provide a more accurate effect estimate using causal inference. We performed a retrospective cross-sectional study with 995 patients with the modified Rankin Scale (mRS) at discharge as the outcome and the EA burden defined as the mean or maximum proportion of time spent with EA in six-hour windows in the first 24 hours of electroencephalography as the exposure. We estimated the change in discharge mRS if everyone in the dataset had experienced a certain EA burden and were untreated. We combined pharmacological modeling with an interpretable matching method to account for confounding and EA-ASM feedback. Our matched groups' quality was validated by the neurologists. Having a maximum EA burden greater than 75% when untreated had a 22% increased chance of a poor outcome (severe disability or death), and mild but long-lasting EA increased the risk of a poor outcome by 14%. The effect sizes were heterogeneous depending on pre-admission profile, e.g., patients with hypoxic-ischemic encephalopathy (HIE) or acquired brain injury (ABI) were more affected. Interventions should put a higher priority on patients with an average EA burden higher than 10%, while treatment should be more conservative when the maximum EA burden is low.

stat.ME↗