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

# From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
Source: [https://arxiv.org/abs/2605.16927](https://arxiv.org/abs/2605.16927)
Authors:[Pujun Feng](https://arxiv.org/search/cs?searchtype=author&query=Feng,+P),[Xiaoyu Guo](https://arxiv.org/search/cs?searchtype=author&query=Guo,+X),[Seyed Ehsan Saffari](https://arxiv.org/search/cs?searchtype=author&query=Saffari,+S+E),[Min Hun Lee](https://arxiv.org/search/cs?searchtype=author&query=Lee,+M+H),[Siew\-Kei Lam](https://arxiv.org/search/cs?searchtype=author&query=Lam,+S),[Erik Cambria](https://arxiv.org/search/cs?searchtype=author&query=Cambria,+E),[Xibin Sun](https://arxiv.org/search/cs?searchtype=author&query=Sun,+X),[Yangtao Zhou](https://arxiv.org/search/cs?searchtype=author&query=Zhou,+Y),[Tong Yang](https://arxiv.org/search/cs?searchtype=author&query=Yang,+T),[Xiaoyu Zhang](https://arxiv.org/search/cs?searchtype=author&query=Zhang,+X),[Tao Tan](https://arxiv.org/search/cs?searchtype=author&query=Tan,+T),[Yue Sun](https://arxiv.org/search/cs?searchtype=author&query=Sun,+Y),[Bin Cui](https://arxiv.org/search/cs?searchtype=author&query=Cui,+B)

[View PDF](https://arxiv.org/pdf/2605.16927)

> 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\.

## Submission history

From: Pujun Feng \[[view email](https://arxiv.org/show-email/4cbe3ff2/2605.16927)\] **\[v1\]**Sat, 16 May 2026 10:45:26 UTC \(27,383 KB\)