arXiv cs.AI· Chuanqi Lao, Junzhou Huang, Qiao Liu·· 3 天前AI 评分22
HiSTOR：面向高维纵向数据的结构化治疗-结局表征学习框架
HiSTOR: Structured Treatment-outcome Representation Learning for High-Dimensional Longitudinal Data
AI 导读
研究者提出 HiSTOR，一个将非线性降维与纵向反事实预测整合的端到端框架，通过按治疗分配与结局的共享及差异关系，学习当前患者状态与演化历史的结构化低维表征。在 CVSim 和 CancerSim 上，HiSTOR 在不同协变量维度、混杂强度和预测时间跨度下均优于现有方法，并支持指定治疗序列下的单步与多步结局预测。
正文 · 原文
Abstract:Estimating potential outcomes under alternative treatment sequences is essential for personalized decision-making, but remains challenging with high-dimensional covariates and time-varying confounding. In this study, we propose HiSTOR (High-dimensional Structured Treatment-Outcome Representation), an end-to-end framework that integrates nonlinear dimension reduction with longitudinal counterfactual prediction. The central idea is to learn structured low-dimensional representations of both current patient states and evolving histories, according to their shared and distinct relationships with treatment assignment and outcomes. This extends latent-space covariate adjustment to longitudinal settings, jointly addressing covariate dimensionality and historical complexity. The resulting framework supports one-step and multi-step outcome prediction under specified treatment sequences. Experiments on CVSim and CancerSim demonstrate the superiority of HiSTOR across varying covariate dimensions, confounding strengths, and prediction horizons compared to state-of-the-art methods. To sum up, HiSTOR offers a unified approach to connecting high-dimensional covariate adjustment with longitudinal potential-outcome prediction.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.17739 [cs.LG] |
| (or arXiv:2610.17739v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17739 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chuanqi Lao [view email]
[v1]
Tue, 13 Oct 2026 05:17:38 UTC (483 KB)
来源：arXiv cs.AI · arxiv.org