Salvato in:
Dettagli Bibliografici
Autori principali: Feng, Pujun, Guo, Xiaoyu, Saffari, Seyed Ehsan, Lee, Min Hun, Lam, Siew-Kei, Cambria, Erik, Sun, Xibin, Zhou, Yangtao, Yang, Tong, Zhang, Xiaoyu, Tan, Tao, Sun, Yue, Cui, Bin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2605.16927
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911690959880192
author Feng, Pujun
Guo, Xiaoyu
Saffari, Seyed Ehsan
Lee, Min Hun
Lam, Siew-Kei
Cambria, Erik
Sun, Xibin
Zhou, Yangtao
Yang, Tong
Zhang, Xiaoyu
Tan, Tao
Sun, Yue
Cui, Bin
author_facet Feng, Pujun
Guo, Xiaoyu
Saffari, Seyed Ehsan
Lee, Min Hun
Lam, Siew-Kei
Cambria, Erik
Sun, Xibin
Zhou, Yangtao
Yang, Tong
Zhang, Xiaoyu
Tan, Tao
Sun, Yue
Cui, Bin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16927
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
Feng, Pujun
Guo, Xiaoyu
Saffari, Seyed Ehsan
Lee, Min Hun
Lam, Siew-Kei
Cambria, Erik
Sun, Xibin
Zhou, Yangtao
Yang, Tong
Zhang, Xiaoyu
Tan, Tao
Sun, Yue
Cui, Bin
Artificial Intelligence
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.
title From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction
topic Artificial Intelligence
url https://arxiv.org/abs/2605.16927