From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
Summary
This review paper proposes a unified framework for intervention-aware disease trajectory modeling in clinical AI, addressing static prediction failures by incorporating treatment confounder feedback and informative observation patterns.
View Cached Full Text
Cached at: 05/19/26, 06:37 AM
# 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 \(27,383 KB\)
Similar Articles
Multimodal Routing for Interpretable, Robust, and Auditable Clinical Prediction
This paper proposes an explicit multimodal routing framework for clinical prediction using EHR data, enabling interpretable, robust, and auditable reasoning across structured variables, clinical notes, and chest X-rays via discrete unimodal, bimodal, and trimodal routes with inference-time route masking for missing modality simulation.
Treatment Response Optimized Clinical Decision Support AI System via Digital Twin Simulation
This paper presents an online adaptive clinical decision support AI system that integrates treatment effect estimation, digital twin simulation, and reinforcement learning to recommend treatments in a safe, clinician-supervised manner, validated on a synthetic simulator and the TCGA ovarian cancer dataset.
DT-Transformer: A Foundation Model for Disease Trajectory Prediction on a Real-world Health System
DT-Transformer is a foundation model trained on 57.1 million structured EHR entries from 1.7 million patients across 11 hospitals in the Mass General Brigham health system, achieving strong discrimination for next-event prediction across 896 disease categories.
Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection
This paper presents Traj-Evolve, a self-evolving multi-agent system that uses an experience pool and multi-agent reinforcement learning to model patient trajectories from longitudinal EHRs for lung cancer early detection, outperforming strong baselines.
A Path-Space Formulation of Prediction in World Models: From a Single Action to Prediction, Planning, and Irreversibility
This paper proposes a path-space formulation of prediction in AI world models, treating the distribution over future trajectories as the fundamental predictive object. It shows that prediction, planning, and uncertainty emerge as operations on a single action functional, and demonstrates that attention asymmetry in learned models correlates with irreversibility in the data.