提出时序反事实框架，解决医疗数据中干预时间依赖问题。
Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma
- 区分不可变与可控特征，建模干预随时间传播
- 38%-67%慢性病患者需生物不可能的假设
- 发现肾心传导链，适合临床决策研究者
反事实推断让医生能提出“如果”类问题，但传统方法假设特征独立且可同时改变——这在纵向临床数据中不成立。我们提出序列反事实框架，通过区分不可变特征（如慢性病）与可控特征（如检验值），建模干预在时间上的传递效应。在2,723例新冠患者（含383例长新冠心衰病例，2,340名匹配对照）上验证，若用朴素方法，38%-67%慢性病患者将产生生物学上不可能的反事实情景。我们识别出肾功能障碍→急性肾损伤→心衰的传导链，每步相对风险分别为2.27和1.19，证明序列反事实能捕捉时间传播机制，而朴素方法无法做到。该框架将反事实解释从‘此特征不同会怎样’升级为‘若早期干预，影响如何递进’，提供基于生物合理性的临床可行动见解。
原文摘要 · Abstract (English)
Counterfactual inference enables clinicians to ask "what if" questions about patient outcomes, but standard methods assume feature independence and simultaneous modifiability -- assumptions violated by longitudinal clinical data. We introduce the Sequential Counterfactual Framework, which respects temporal dependencies in electronic health records by distinguishing immutable features (chronic diagnoses) from controllable features (lab values) and modeling how interventions propagate through time. Applied to 2,723 COVID-19 patients (383 Long COVID heart failure cases, 2,340 matched controls), we demonstrate that 38-67% of patients with chronic conditions would require biologically impossible counterfactuals under naive methods. We identify a cardiorenal cascade (CKD -> AKI -> HF) with relative risks of 2.27 and 1.19 at each step, illustrating temporal propagation that sequential -- but not naive -- counterfactuals can capture. Our framework transforms counterfactual explanation from "what if this feature were different?" to "what if we had intervened earlier, and how would that propagate forward?" -- yielding clinically actionable insights grounded in biological plausibility.
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。