Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma

Jingya Cheng; Alaleh Azhir; Jiazi Tian; Hossein Estiri

cs.LGFeb 24, 2026

Sequential Counterfactual Inference for Temporal Clinical Data: Addressing the Time Traveler Dilemma

Authors: Jingya Cheng, Alaleh Azhir, Jiazi Tian, Hossein Estiri

Organizations: Massachusetts General Hospital, Boston, MA, USA

Abstract

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.

Figures & tables

Conditions at History (pre-COVID)
Characteristic	N	%
Total patients	2,723	100.0
Cases (Long COVID HF)	383	14.1
Controls	2,340	85.9
Hypertension (I10)	2,152	79.0
Type 2 Diabetes (E11)	1,239	45.5

Table 1: Cohort Characteristics

Figure 1: Temporal persistence of chronic conditions. Probability of diagnosis in Last period given presence (red) or absence (blue) in History. The 6–13 $\times$ differences demonstrate temporal dependencies.

Patient-level violations (at least one feature affected)
Constraint	Definition	N	%
P1: Immutability	Chronic dx in HISTORY persists to LAST	1,481	54.4
P2: Temporal Coherence	Controllable feature lacks intervention pathway	328	12.0
Any violation	At least one implausible CF required	1,561	57.3
Feature-level P1 violations (diagnosis persistence)
Hypertension (I10)	Present in both HISTORY and LAST	1,120/1,172	95.6

Table 2: Plausibility Violations by Constraint Type

Figure 2: Cardiorenal cascade. Top : Flow diagram showing CKD $\rightarrow$ AKI (RR=2.27) $\rightarrow$ HF (RR=1.19). Bottom : Naive vs. sequential approaches.

Counterfactual Explanations

Counterfactual explanations show how changing an input could alter a model’s prediction, supporting model understanding, auditing, and actionable recourse.

See all 109 papers

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions
Jun 4, 2026Wenhao Mu, Facundo Yan, Anik Mumssen +2Forecasting Benchmarks Counterfactual Prediction
University of Michigan · Computer Science and Engineering · Ann Arbor, Michigan, USA +1
Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data
Apr 14, 2026Farbod Alinezhad, Jianfei Cao, Gary J. Young +1Counterfactual Prediction Causal Inference
Analysis Group · Department of Economics, Northeastern University · Center for Health Policy and Healthcare Research, Northeastern University +1
Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction
Jun 4, 2026Amirhossein Zare, Amirhessam Zare, Herlock Rahimi +2Structural Causal Models Counterfactual Prediction
School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. · Department of Electrical and Computer Engineering, Yale University, New Haven, CT, USA. · School of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran. +2

Jun 4, 2026J/K move · Enter open · S save

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions

Wenhao Mu, Facundo Yan, Anik Mumssen, Marisa Eisenberg+1

University of Michigan · Computer Science and Engineering · Ann Arbor, Michigan, USA+1

Forecasting Benchmarks Counterfactual Prediction Counterfactual Learning Causal Intervention Spatial Epidemic Modeling

Open paper AskPDF arXiv

Deep learning has enabled significant advances in time-series causal inference, yet progress remains constrained by the lack of realistic benchmarks with observable counterfactual outcomes. Existing datasets either rely on real-world observations without ground-truth counterfactuals or on simplified simulations that fail to capture complex causal dynamics. To address this gap, we develop a large-scale benchmark for counterfactual prediction in epidemic time series under dynamic interventions. Unlike existing benchmarks, it supports static and time-varying treatments, as well as both single-policy and multi-policy intervention settings, enabling evaluation of causal inference methods across a broad range of causal inference scenarios. Leveraging a calibrated agent-based model grounded in real-world demographic, mobility, epidemiological, and policy data, we generate realistic counterfactual trajectories across more than 150 U.S. counties. Using this benchmark, we evaluate widely used and state-of-the-art causal inference methods, revealing substantial performance differences and highlighting the challenges of realistic time-series causal reasoning.

Abstract

Counterfactual Explanations

Explore similar work

Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions

Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data

Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction