From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction

TL;DR

This paper reviews and unifies methods for modeling disease trajectories in clinical AI, emphasizing intervention-aware approaches that account for treatment effects, confounding, and observational biases to improve decision-making.

Contribution

It introduces a comprehensive framework linking forecasting, counterfactual analysis, and policy evaluation, advancing clinical prediction towards decision-grade evidence.

Findings

Unified framework for disease trajectory modeling

Mapping of key method families to decision components

Evaluation strategies for treatment-sensitive predictions

Abstract

Clinical decision-making is a feedback system where risk estimates influence treatment, which in turn changes disease trajectories, and both shape clinicians' measurement practices. Static prediction often fails clinically: models trained on observational care logs conflate disease biology with clinician behavior, particularly under treatment confounder feedback and irregular or informative observation. This Review focuses on intervention-aware disease trajectory modeling in clinical AI--methods estimating patient-specific longitudinal disease evolution and assessing trajectory changes under alternative treatments. We organize the field around six linked components: three decision tasks (factual forecasting, counterfactual estimation, policy evaluation) and three data-generating mechanisms (disease evolution, treatment assignment, observation process) that determine identifiability. We present the first unified framework bridging forecasting, counterfactual trajectories, and policy evaluation across discrete/continuous time, explicitly addressing treatment assignment, time-varying confounding, and observation bias. We synthesize key method families (multistate/joint models, temporal point-process, deep sequence architectures, longitudinal causal inference), map them to relevant components, and align evaluation with claim strength via overlap diagnostics, uncertainty quantification, off-policy robustness, and target-trial validation. This synthesis advances benchmark prediction to decision-grade clinical evidence, enabling treatment-sensitive individualized futures, pre-deployment policy stress-testing, and safer closed-loop learning health systems that adapt/abstain when evidence is insufficient.