arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05504cs.LG
收藏

G-Transformer:动态和时变治疗方案下的反事实结果预测

G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimes

Harvard University(哈佛大学);Massachusetts Institute of Technology(麻省理工学院);City University of New York(纽约城市大学);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)

Hong Xiong, Feng Wu, Leon Deng, Megan Su, Li-wei H Lehman

AI总结:

本文提出G-Transformer,一种基于Transformer架构并结合g-computation因果推断方法的模型,用于在动态和时变治疗方案下进行反事实结果预测,在模拟与真实ICU数据集上均优于现有模型。

摘要:

在医疗决策背景下,反事实预测使临床医生能够在给定观察到的患者历史的情况下,预测替代治疗行动方案下的治疗结果。在这项工作中,我们提出了G-Transformer,用于动态和时变治疗策略下的反事实结果预测。我们的方法利用Transformer架构捕获时变协变量中复杂的长期依赖关系,同时实现g-computation(一种用于估计动态治疗策略效果的因果推断方法)。具体而言,我们使用基于Transformer的编码器架构,在每个时间点给定协变量和治疗历史的情况下估计相关协变量的条件分布,然后通过模拟在感兴趣治疗策略下向前推进的患者轨迹,生成反事实结果的蒙特卡洛估计。我们使用来自机制模型的两个模拟纵向数据集,以及来自MIMIC-IV的真实世界脓毒症ICU数据集,对G-Transformer进行了广泛评估。在这些设置中,G-Transformer的表现均优于经典和最先进的反事实预测模型。据我们所知,这是首个支持g-computation以进行动态和时变治疗策略下反事实结果预测的基于Transformer的架构。

英文摘要:

In the context of medical decision making, counterfactual prediction enables clinicians to predict treatment outcomes of interest under alternative courses of therapeutic actions given observed patient history. In this work, we present G-Transformer for counterfactual outcome prediction under dynamic and time-varying treatment strategies. Our approach leverages a Transformer architecture to capture complex, long-range dependencies in time-varying covariates while enabling g-computation, a causal inference method for estimating the effects of dynamic treatment regimes. Specifically, we use a Transformer-based encoder architecture to estimate the conditional distribution of relevant covariates given covariate and treatment history at each time point, then produces Monte Carlo estimates of counterfactual outcomes by simulating forward patient trajectories under treatment strategies of interest. We evaluate G-Transformer extensively using two simulated longitudinal datasets from mechanistic models, and a real-world sepsis ICU dataset from MIMIC-IV. G-Transformer outperforms both classical and state-of-the-art counterfactual prediction models in these settings. To the best of our knowledge, this is the first Transformer-based architecture that supports g-computation for counterfactual outcome prediction under dynamic and time-varying treatment strategies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑