首个可端到端训练的治疗效应时序估计框架，突破传统方法限制。
DeepBlip: Estimating Conditional Average Treatment Effects Over Time
- 创新双优化技巧，实现所有局部治疗效应函数同步学习
- 在多个临床数据集上达到当前最优性能，误差显著降低
- 适合需要精准评估长期治疗策略的医疗决策研究者
结构化嵌套均值模型（SNMM）是一种合理估算随时间变化的治疗效应的方法。其核心优势在于将治疗序列的联合效应分解为局部的、时间特定的“局部效应”（blip effects），从而提升结果可解释性，并支持无需重算的高效离线最优治疗策略评估。然而，由于其固有的顺序g-估计机制，现有神经网络框架难以实现端到端的梯度训练。本文提出DeepBlip，首个面向SNMM的神经框架，通过新颖的双重优化技巧，实现所有局部效应函数的联合学习。DeepBlip可无缝集成如LSTM或Transformer等序列神经网络以捕捉复杂时序依赖。设计上，该方法能正确调整时变混杂因素，获得无偏估计；其奈曼正交损失函数确保对辅助模型误设具有鲁棒性。我们在多个临床数据集上评估DeepBlip，结果表明其性能达到当前最佳水平。
原文摘要 · Abstract (English)
Structural nested mean models (SNMMs) are a principled approach to estimate the treatment effects over time. A particular strength of SNMMs is to break the joint effect of treatment sequences over time into localized, time-specific ``blip effects''. This decomposition promotes interpretability through the incremental effects and enables the efficient offline evaluation of optimal treatment policies without re-computation. However, neural frameworks for SNMMs are lacking, as their inherently sequential g-estimation scheme prevents end-to-end, gradient-based training. Here, we propose DeepBlip, the first neural framework for SNMMs, which overcomes this limitation with a novel double optimization trick to enable simultaneous learning of all blip functions. Our DeepBlip seamlessly integrates sequential neural networks like LSTMs or transformers to capture complex temporal dependencies. By design, our method correctly adjusts for time-varying confounding to produce unbiased estimates, and its Neyman-orthogonal loss function ensures robustness to nuisance model misspecification. Finally, we evaluate our DeepBlip across various clinical datasets, where it achieves state-of-the-art performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。