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

TL;DR

This paper introduces a sequential counterfactual inference framework for longitudinal clinical data, capturing temporal dependencies and intervention propagation, enabling more realistic and actionable clinical insights.

Contribution

The paper presents a novel framework that models temporal dependencies in counterfactual inference for clinical data, addressing limitations of naive methods and improving biological plausibility.

Findings

Identified that naive methods produce impossible counterfactuals for many patients.

Discovered a cardiorenal cascade with significant relative risks.

Demonstrated the framework's ability to generate clinically actionable insights.

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.