Longitudinal treatment decisions from multivariate time-series data require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data. Existing longitudinal causal estimators typically address this problem by training a new model for each cohort or simulator. We introduce Causal Longitudinal Prior-Fitted Networks (CausalLongPFN), a prior-fitted network for time-series causal inference in longitudinal treatment-response data and zero-shot in-context counterfactual outcome prediction. The model is pretrained entirely on synthetic episodes sampled from a broad prior over temporal structural causal models, exposing it to treatment-confounder feedback, latent heterogeneity, nonlinear state evolution, delayed effects, and cumulative treatment responses. At test time, CausalLongPFN remains frozen and is used zero-shot: it conditions on support trajectories, a query history, and a planned future treatment sequence, and returns a predictive distribution over future outcomes without gradient updates or propensity-model fitting. Multi-step predictions are obtained by recursively applying the one-step predictor under the specified treatment sequence. We evaluate the model on branchable cancer, HIV, and warfarin benchmarks with ground-truth counterfactual labels, and on factual-only rolling-origin prediction in MIMIC-III ICU trajectories. CausalLongPFN is competitive with domain-trained longitudinal baselines on counterfactual benchmarks and performs strongly on factual MIMIC-III prediction, suggesting that broad synthetic causal pretraining can provide a frozen, amortized alternative for zero-shot longitudinal treatment-response prediction when repeated domain-specific training is costly or impractical.

翻译：多变量时间序列数据中的纵向治疗决策要求在存在时变混杂、异质性患者动态及有限领域特定数据的条件下，预测未来治疗序列下的潜在结局。现有纵向因果估计方法通常通过为每个队列或模拟器训练新模型来解决此问题。我们提出因果纵向先验拟合网络（CausalLongPFN），这是一种针对纵向治疗-反应数据中时间序列因果推断及零样本上下文反事实结局预测的先验拟合网络。该模型完全基于从时间结构因果模型的广义先验中采样的合成片段进行预训练，使其暴露于治疗-混杂反馈、潜在异质性、非线性状态演化、延迟效应及累积治疗反应。在测试阶段，CausalLongPFN保持冻结状态并用于零样本推断：它基于支持轨迹、查询历史及计划未来治疗序列进行条件预测，无需梯度更新或倾向性模型拟合即可返回未来结局的预测分布。通过在指定治疗序列下递归应用单步预测器实现多步预测。我们在具有真实反事实标签的可分支癌症、HIV及华法林基准数据集上评估模型，并在MIMIC-III ICU轨迹的事实滚动起源预测中验证性能。CausalLongPFN在反事实基准上可与领域训练的纵向基线模型媲美，并在MIMIC-III事实预测中表现优异，表明广泛合成因果预训练可提供一种冻结的摊销替代方案，适用于重复领域训练成本高昂或不切实际的零样本纵向治疗-反应预测场景。