Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction

• URL: http://arxiv.org/abs/2606.05797v2
• Date: Sun, 07 Jun 2026 11:10:09 GMT
• Title: Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction
• Abstract summary: We introduce Causal Longitudinal Prior-Fitted Networks (CausalLongPFN) for time-series causal inference in longitudinal treatment-response data.<n>CausalLongPFN is a prior-fitted network for time-series causal inference in longitudinal treatment-response data and zero-shot in-context counterfactual outcome prediction.<n>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.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data [0.0]
  Causal Diffusion Model (CDM) generates full probabilistic distributions of counterfactual outcomes under sequential interventions.<n>CDM consistently outperforms state-of-the-art longitudinal causal inference methods.
  arXiv  Detail & Related papers  (2026-04-14T17:25:53Z)
• TimeAPN: Adaptive Amplitude-Phase Non-Stationarity Normalization for Time Series Forecasting [67.91113180885601]
  TimeAPN explicitly models and predicts non-stationary factors from both the time and frequency domains.<n>TimeAPN consistently improves long-term forecasting accuracy across multiple prediction horizons.<n>It outperforms state-of-the-art reversible normalization methods.
  arXiv  Detail & Related papers  (2026-03-18T07:21:24Z)
• Conformal Prediction for Dose-Response Models with Continuous Treatments [0.23213238782019321]
  We present a novel methodology for generating prediction intervals for dose-response models. Our method approximates local coverage for every treatment value by applying kernel functions as weights in weighted conformal prediction.
  arXiv  Detail & Related papers  (2024-09-30T15:40:54Z)
• Estimating Long-term Heterogeneous Dose-response Curve: Generalization Bound Leveraging Optimal Transport Weights [54.65531750162626]
  Long-term treatment effect estimation is a significant but challenging problem in many applications.<n>Existing methods rely on ideal assumptions, such as no unobserved confounders or binary treatment, to estimate long-term average treatment effects.<n>We introduce an optimal transport weighting framework to align the long-term observational data to an auxiliary short-term experimental data.
  arXiv  Detail & Related papers  (2024-06-27T14:13:46Z)
• Conditional Score-Based Diffusion Model for Cortical Thickness Trajectory Prediction [29.415616701032604]
  Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals. We propose a conditional score-based diffusion model to generate CTh trajectories with the given baseline information. Our model has a near-zero bias with narrow confidential 95% interval compared to the ground-truth CTh in 6-36 months.
  arXiv  Detail & Related papers  (2024-03-11T17:26:18Z)
• Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment [72.50906475214457]
  The goal of sequential event prediction is to estimate the next event based on a sequence of historical events. In practice, the next-event prediction models are trained with sequential data collected at one time. We propose a framework with hierarchical branching structures for learning context-specific representations.
  arXiv  Detail & Related papers  (2022-10-24T07:54:13Z)
• Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations [84.42837346400151]
  Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare. Existing causal inference approaches consider regular, discrete-time intervals between observations and treatment decisions. We propose a controllable simulation environment based on a model of tumor growth for a range of scenarios.
  arXiv  Detail & Related papers  (2022-06-16T17:15:15Z)
• Predicting the impact of treatments over time with uncertainty aware neural differential equations [2.099922236065961]
  We propose Counterfactual ODE, a novel method to predict the impact of treatments continuously over time. We demonstrate over several longitudinal data sets that CF-ODE provides more accurate predictions and more reliable uncertainty estimates than previously available methods.
  arXiv  Detail & Related papers  (2022-02-24T09:50:02Z)
• When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting [70.54920804222031]
  Most existing forecasting models disregard uncertainty quantification, resulting in mis-calibrated predictions. Recent works in deep neural models for uncertainty-aware time-series forecasting also have several limitations. We model the forecasting task as a probabilistic generative process and propose a functional neural process model called EPIFNP.
  arXiv  Detail & Related papers  (2021-06-07T18:31:47Z)
• STELAR: Spatio-temporal Tensor Factorization with Latent Epidemiological Regularization [76.57716281104938]
  We develop a tensor method to predict the evolution of epidemic trends for many regions simultaneously. STELAR enables long-term prediction by incorporating latent temporal regularization through a system of discrete-time difference equations. We conduct experiments using both county- and state-level COVID-19 data and show that our model can identify interesting latent patterns of the epidemic.
  arXiv  Detail & Related papers  (2020-12-08T21:21:47Z)
• DeepRite: Deep Recurrent Inverse TreatmEnt Weighting for Adjusting Time-varying Confounding in Modern Longitudinal Observational Data [68.29870617697532]
  We propose Deep Recurrent Inverse TreatmEnt weighting (DeepRite) for time-varying confounding in longitudinal data. DeepRite is shown to recover the ground truth from synthetic data, and estimate unbiased treatment effects from real data.
  arXiv  Detail & Related papers  (2020-10-28T15:05:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.