Recent Advances, Applications, and Open Challenges in Machine Learning for Health: Reflections from Research Roundtables at ML4H 2023 Symposium

The third ML4H symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA. The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the \ac{ML4H} community. Encouraged by the successful virtual roundtables in the previous year, we organized eleven in-person roundtables and four virtual roundtables at ML4H 2022. The organization of the research roundtables at the conference involved 17 Senior Chairs and 19 Junior Chairs across 11 tables. Each roundtable session included invited senior chairs (with substantial experience in the field), junior chairs (responsible for facilitating the discussion), and attendees from diverse backgrounds with interest in the session's topic. Herein we detail the organization process and compile takeaways from these roundtable discussions, including recent advances, applications, and open challenges for each topic. We conclude with a summary and lessons learned across all roundtables. This document serves as a comprehensive review paper, summarizing the recent advancements in machine learning for healthcare as contributed by foremost researchers in the field.

Predictive Churn with the Set of Good Models

Machine learning models in modern mass-market applications are often updated over time. One of the foremost challenges faced is that, despite increasing overall performance, these updates may flip specific model predictions in unpredictable ways. In practice, researchers quantify the number of unstable predictions between models pre and post update -- i.e., predictive churn. In this paper, we study this effect through the lens of predictive multiplicity -- i.e., the prevalence of conflicting predictions over the set of near-optimal models (the Rashomon set). We show how traditional measures of predictive multiplicity can be used to examine expected churn over this set of prospective models -- i.e., the set of models that may be used to replace a baseline model in deployment. We present theoretical results on the expected churn between models within the Rashomon set from different perspectives. And we characterize expected churn over model updates via the Rashomon set, pairing our analysis with empirical results on real-world datasets -- showing how our approach can be used to better anticipate, reduce, and avoid churn in consumer-facing applications. Further, we show that our approach is useful even for models enhanced with uncertainty awareness.

Learning from Time Series under Temporal Label Noise

Many sequential classification tasks are affected by label noise that varies over time. Such noise can cause label quality to improve, worsen, or periodically change over time. We first propose and formalize temporal label noise, an unstudied problem for sequential classification of time series. In this setting, multiple labels are recorded in sequence while being corrupted by a time-dependent noise function. We first demonstrate the importance of modelling the temporal nature of the label noise function and how existing methods will consistently underperform. We then propose methods that can train noise-tolerant classifiers by estimating the temporal label noise function directly from data. We show that our methods lead to state-of-the-art performance in the presence of diverse temporal label noise functions using real and synthetic data.

FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning

Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the recommendations as well as the recommendations of other users. In applications like healthcare, housing, and finance, this sensitivity can have adverse effects on user experience. We propose a method to stabilize a given recommender system against such perturbations. This is a challenging task due to (1) the lack of a ``reference'' rank list that can be used to anchor the outputs; and (2) the computational challenges in ensuring the stability of rank lists with respect to all possible perturbations of training data. Our method, FINEST, overcomes these challenges by obtaining reference rank lists from a given recommendation model and then fine-tuning the model under simulated perturbation scenarios with rank-preserving regularization on sampled items. Our experiments on real-world datasets demonstrate that FINEST can ensure that recommender models output stable recommendations under a wide range of different perturbations without compromising next-item prediction accuracy.

Prediction without Preclusion: Recourse Verification with Reachable Sets

Machine learning models are often used to decide who will receive a loan, a job interview, or a public benefit. Standard techniques to build these models use features about people but overlook their actionability. In turn, models can assign predictions that are fixed, meaning that consumers who are denied loans, interviews, or benefits may be permanently locked out from access to credit, employment, or assistance. In this work, we introduce a formal testing procedure to flag models that assign fixed predictions that we call recourse verification. We develop machinery to reliably determine if a given model can provide recourse to its decision subjects from a set of user-specified actionability constraints. We demonstrate how our tools can ensure recourse and adversarial robustness in real-world datasets and use them to study the infeasibility of recourse in real-world lending datasets. Our results highlight how models can inadvertently assign fixed predictions that permanently bar access, and we provide tools to design algorithms that account for actionability when developing models.

Algorithmic Censoring in Dynamic Learning Systems

Dynamic learning systems subject to selective labeling exhibit censoring, i.e. persistent negative predictions assigned to one or more subgroups of points. In applications like consumer finance, this results in groups of applicants that are persistently denied and thus never enter into the training data. In this work, we formalize censoring, demonstrate how it can arise, and highlight difficulties in detection. We consider safeguards against censoring - recourse and randomized-exploration - both of which ensure we collect labels for points that would otherwise go unobserved. The resulting techniques allow examples from censored groups to enter into the training data and correct the model. Our results highlight the otherwise unmeasured harms of censoring and demonstrate the effectiveness of mitigation strategies across a range of data generating processes.

Participatory Systems for Personalized Prediction

Machine learning models are often personalized based on information that is protected, sensitive, self-reported, or costly to acquire. These models use information about people, but do not facilitate nor inform their \emph{consent}. Individuals cannot opt out of reporting information that a model needs to personalize their predictions, nor tell if they would benefit from personalization in the first place. In this work, we introduce a new family of prediction models, called \emph{participatory systems}, that allow individuals to opt into personalization at prediction time. We present a model-agnostic algorithm to learn participatory systems for supervised learning tasks where models are personalized with categorical group attributes. We conduct a comprehensive empirical study of participatory systems in clinical prediction tasks, comparing them to common approaches for personalization and imputation. Our results demonstrate that participatory systems can facilitate and inform consent in a way that improves performance and privacy across all groups who report personal data.

When Personalization Harms: Reconsidering the Use of Group Attributes in Prediction

The standard approach to personalization in machine learning consists of training a model with group attributes like sex, age group, and blood type. In this work, we show that this approach to personalization fails to improve performance for all groups who provide personal data. We discuss how this effect inflicts harm in applications where models assign predictions on the basis of group membership. We propose collective preference guarantees to ensure the fair use of group attributes in prediction. We characterize how common approaches to personalization violate fair use due to failures in model development and deployment. We conduct a comprehensive empirical study of personalization in clinical prediction models. Our results highlight the prevalence of fair use violations, demonstrate actionable interventions to mitigate harm and underscore the need to measure the gains of personalization for all groups who provide personal data.

Predictive Multiplicity in Probabilistic Classification

For a prediction task, there may exist multiple models that perform almost equally well. This multiplicity complicates how we typically develop and deploy machine learning models. We study how multiplicity affects predictions -- i.e., predictive multiplicity -- in probabilistic classification. We introduce new measures for this setting and present optimization-based methods to compute these measures for convex empirical risk minimization problems like logistic regression. We apply our methodology to gain insight into why predictive multiplicity arises. We study the incidence and prevalence of predictive multiplicity in real-world risk assessment tasks. Our results emphasize the need to report multiplicity more widely.

Learning Optimal Predictive Checklists

Checklists are simple decision aids that are often used to promote safety and reliability in clinical applications. In this paper, we present a method to learn checklists for clinical decision support. We represent predictive checklists as discrete linear classifiers with binary features and unit weights. We then learn globally optimal predictive checklists from data by solving an integer programming problem. Our method allows users to customize checklists to obey complex constraints, including constraints to enforce group fairness and to binarize real-valued features at training time. In addition, it pairs models with an optimality gap that can inform model development and determine the feasibility of learning sufficiently accurate checklists on a given dataset. We pair our method with specialized techniques that speed up its ability to train a predictive checklist that performs well and has a small optimality gap. We benchmark the performance of our method on seven clinical classification problems, and demonstrate its practical benefits by training a short-form checklist for PTSD screening. Our results show that our method can fit simple predictive checklists that perform well and that can easily be customized to obey a rich class of custom constraints.