arXiv subjects

Yunshan Duan

Publications and source records attributed to Yunshan Duan.

5 recordsLinked to original sources

arXiv2026

Self-Supervised Representation Learning for Longitudinal Polypharmacy Patterns

Polypharmacy, commonly defined as the concurrent use of multiple medications, is increasingly prevalent in aging populations and is associated with adverse health outcomes. Motivated by longitudinal studies of aging people with HIV (PWH), we study how medication use evolves over time and characterizes multimorbidity patterns. Longitudinal medication data present substantial methodological challenges, including high dimensionality, sparsity, irregular observation times, and structured pharmacologic relationships among medications. Existing approaches are typically task-specific and lack a unified framework for learning general-purpose representations of medication trajectories. We propose LOPEL (LOngitudinal Polypharmacy Embedding Learning), a two-stage self-supervised framework for learning low-dimensional representations of longitudinal medication data. In the first stage, visit-level embeddings are learned using a Gaussian process model that incorporates pharmacologic similarity through the Anatomical Therapeutic Chemical hierarchy. In the second stage, subject-level embeddings are constructed by modeling trajectories over time and defining similarity through a Wasserstein-based representation capturing temporal dynamics and uncertainty. Simulation studies demonstrate that LOPEL accurately recovers latent structure under realistic conditions with high-dimensional sparsity and irregular sampling. In an application to aging cohorts of PWH, LOPEL identifies clinically meaningful subgroups that differ in the timing, composition, and progression of medication use, highlighting heterogeneity relevant for risk stratification and clinical management.

stat.ME↗

arXiv2025

Self-Supervised Learning with Gaussian Processes

Self supervised learning (SSL) is a machine learning paradigm where models learn to understand the underlying structure of data without explicit supervision from labeled samples. The acquired representations from SSL have demonstrated useful for many downstream tasks including clustering, and linear classification, etc. To ensure smoothness of the representation space, most SSL methods rely on the ability to generate pairs of observations that are similar to a given instance. However, generating these pairs may be challenging for many types of data. Moreover, these methods lack consideration of uncertainty quantification and can perform poorly in out-of-sample prediction settings. To address these limitations, we propose Gaussian process self supervised learning (GPSSL), a novel approach that utilizes Gaussian processes (GP) models on representation learning. GP priors are imposed on the representations, and we obtain a generalized Bayesian posterior minimizing a loss function that encourages informative representations. The covariance function inherent in GPs naturally pulls representations of similar units together, serving as an alternative to using explicitly defined positive samples. We show that GPSSL is closely related to both kernel PCA and VICReg, a popular neural network-based SSL method, but unlike both allows for posterior uncertainties that can be propagated to downstream tasks. Experiments on various datasets, considering classification and regression tasks, demonstrate that GPSSL outperforms traditional methods in terms of accuracy, uncertainty quantification, and error control.

cs.LG↗

arXiv2022

A Comparative Tutorial of Bayesian Sequential Design and Reinforcement Learning

Reinforcement Learning (RL) is a computational approach to reward-driven learning in sequential decision problems. It implements the discovery of optimal actions by learning from an agent interacting with an environment rather than from supervised data. We contrast and compare RL with traditional sequential design, focusing on simulation-based Bayesian sequential design (BSD). Recently, there has been an increasing interest in RL techniques for healthcare applications. We introduce two related applications as motivating examples. In both applications, the sequential nature of the decisions is restricted to sequential stopping. Rather than a comprehensive survey, the focus of the discussion is on solutions using standard tools for these two relatively simple sequential stopping problems. Both problems are inspired by adaptive clinical trial design. We use examples to explain the terminology and mathematical background that underlie each framework and map one to the other. The implementations and results illustrate the many similarities between RL and BSD. The results motivate the discussion of the potential strengths and limitations of each approach.

stat.ME↗

arXiv2021

A Unified Decision Framework for Phase I Dose-Finding Designs

The purpose of a phase I dose-finding clinical trial is to investigate the toxicity profiles of various doses for a new drug and identify the maximum tolerated dose. Over the past three decades, various dose-finding designs have been proposed and discussed, including conventional model-based designs, new model-based designs using toxicity probability intervals, and rule-based designs. We present a simple decision framework that can generate several popular designs as special cases. We show that these designs share common elements under the framework, such as the same likelihood function, the use of loss functions, and the nature of the optimal decisions as Bayes rules. They differ mostly in the choice of the prior distributions. We present theoretical results on the decision framework and its link to specific and popular designs like mTPI, BOIN, and CRM. These results provide useful insights into the designs and their underlying assumptions, and convey information to help practitioners select an appropriate design.

stat.ME↗

arXiv2020

Hi3+3: A Model-Assisted Dose-Finding Design Borrowing Historical Data

Background -- In phase I clinical trials, historical data may be available through multi-regional programs, reformulation of the same drug, or previous trials for a drug under the same class. Statistical designs that borrow information from historical data can reduce cost, speed up drug development, and maintain safety. Purpose -- Based on a hybrid design that partly uses probability models and partly uses algorithmic rules for decision making, we aim to improve the efficiency of the dose-finding trials in the presence of historical data, maintain safety for patients, and achieve a level of simplicity for practical applications. Methods -- We propose the Hi3+3 design, in which the letter "H" represents "historical data". We apply the idea in power prior to borrow historical data and define the effective sample size (ESS) of the prior. Dose-finding decision rules follow the idea in the i3+3 design while incorporating the historical data via the power prior and ESS. The proposed Hi3+3 design pretabulates the dosing decisions before the trial starts, a desirable feature for ease of application in practice. Results -- The Hi3+3 design is superior than the i3+3 design due to information borrow from historical data. It is capable of maintaining a high level of safety for trial patients without sacrificing the ability to identify the correct MTD. Illustration of this feature are found in the simulation results. Conclusion -- With the demonstrated safety, efficiency, and simplicity, the Hi3+3 design could be a desirable choice for dose-finding trials borrowing historical data.

stat.ME↗