CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning

Title: CaMeWM: A Causal Medical World Model for Generative Tumor Evolution and Treatment Planning

标题：CaMeWM：用于生成式肿瘤演变与治疗规划的因果医学世界模型

Abstract: Treatment planning is intrinsically counterfactual: clinicians must compare how a patient’s tumor and survival would evolve under competing regimens, whereas a retrospective cohort records only the regimen received and one follow-up scan. A treatment-conditioned generator trained on such data can therefore reproduce historical treatment allocation rather than simulate the interventional disease dynamics needed to rank regimens.

摘要：治疗规划本质上是反事实的：临床医生必须比较患者的肿瘤和生存状况在不同治疗方案下将如何演变，而回顾性队列研究仅记录了患者所接受的治疗方案及一次随访扫描。因此，在这些数据上训练的治疗条件生成器只能重现历史治疗分配，而无法模拟对评估治疗方案至关重要的干预性疾病动态。

We introduce \textbf{CaMeWM}, a causal medical world model for supported post-TACE tumor evolution and treatment planning. CaMeWM implements one intervention-to-decision loop rather than three independent prediction tasks: it first admits a queried regimen only for clinically comparable histories with empirical treatment support; it then generates a distribution of lesion-local follow-up worlds through an action-conditioned response descriptor, deterministic anchor, and residual 3D diffusion transition; and it finally maps sampled worlds to restricted mean survival time (RMST) with a response-Cox utility model.

我们引入了 \textbf{CaMeWM}，这是一种用于支持 TACE（经导管动脉化疗栓塞）后肿瘤演变与治疗规划的因果医学世界模型。CaMeWM 实现了一个“干预到决策”的循环，而非三个独立的预测任务：首先，它仅针对具有经验性治疗支持且临床可比的病史接纳查询的治疗方案；随后，通过动作条件响应描述符、确定性锚点和残差 3D 扩散转换，生成病灶局部随访世界的分布；最后，利用响应-Cox 效用模型将采样世界映射到限制性平均生存时间 (RMST)。

Under pre-treatment adjustment and positivity, this loop estimates a prespecified, support-restricted g-formula target; all selection and nuisance estimation are fold-local, and the induced policy is evaluated by cross-fitted, censoring-adjusted doubly robust estimation. Across 79 paired out-of-fold episodes, CaMeWM achieves 0.618 SSIM and 0.528 change-map SSIM for follow-up CT transition, while its generated-world survival pathway attains a 0.615 C-index; factual-only AIPW estimates a 9.60-week RMST gain (95% CI 0.61—18.13) for the frozen policy. CaMeWM provides an inspectable basis for retrospective, support-restricted treatment planning.

在预处理调整和正性条件下，该循环估计了一个预先指定的、支持受限的 g-公式目标；所有选择和干扰估计均为折叠局部（fold-local），且诱导策略通过交叉拟合、经删失调整的双重稳健估计进行评估。在 79 个配对的折外（out-of-fold）片段中，CaMeWM 在随访 CT 转换方面实现了 0.618 的 SSIM 和 0.528 的变化图 SSIM，其生成的生存路径达到了 0.615 的 C-index；仅基于事实的 AIPW 估计显示，对于固定策略，RMST 增加了 9.60 周（95% CI 0.61—18.13）。CaMeWM 为回顾性、支持受限的治疗规划提供了一个可检查的基础。