多模态干预轨迹的可容许扩散
Admissible Diffusion for Multimodal Interventional Trajectories
- Johns Hopkins University（约翰斯·霍普金斯大学）
- Massachusetts Institute of Technology（麻省理工学院）
- Bayesian Health（贝叶斯健康）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ADMIT框架结合多模态表示、治疗条件潜在扩散和显式约束，通过可容许机制生成干预轨迹，实验表明其改善隐藏状态恢复并预测剂量重分配效应。
AI中文摘要：
生成一条合理的临床轨迹并不能确定在不同治疗下会发生什么。我们提出了ADMIT，一个结合不规则多模态表示、治疗条件潜在扩散以及对生成状态或动作的显式约束的框架。我们通过顺序g计算来表述其干预目标，并区分因果假设与约束满足。其可容许性机制将生理先验知识转化为对生成状态和提议动作的显式约束。治疗暴露动态条件化潜在转换，而状态投影或动作门控在轨迹生成过程中应用约束，从而影响后续轨迹生成。在我们的初步实验中，多模态输入改善了监督下的隐藏状态恢复，并减少了治疗对比误差。在模拟的给药方案实验中，采用无泄漏历史编码，ADMIT预测了因重新分配固定总剂量而引起的肿瘤体积变化的大部分。暴露输入在临时剂量减少期间改善了这些预测，无论假设的清除率是否正确，但降低了预测的剂量效应大小，而确定性递归基线匹配了ADMIT的平均预测。暴露投影减少了约束违反，尽管执行仍不完整。使用eICU背景的半合成实验说明了在固定和自适应策略下的治疗反应生成。观察性例子进一步表征了模型治疗敏感性。ADMIT提供了一个框架，用于测试互补观察和生理限制是否改善干预轨迹，并分别评估表示恢复、效应准确性和规则执行。
英文摘要：
Generating a plausible clinical trajectory does not establish what would happen under a different treatment. We present ADMIT, a framework combining irregular multimodal representations, treatment-conditioned latent diffusion and explicit constraints on generated states or actions. We formulate its interventional target through sequential g-computation and distinguish causal assumptions from constraint satisfaction. Its admissibility mechanism translates physiological prior knowledge into explicit constraints on generated states and proposed actions. Treatment-exposure dynamics condition latent transitions, while state projection or action gating applies the constraints during rollout so that they influence subsequent trajectory generation. In our preliminary experiments, multimodal inputs improved supervised hidden-state recovery and reduced treatment-contrast error. In a simulated dosing-schedule experiment with leak-free history encoding, ADMIT predicted most of the tumor-volume change caused by redistributing a fixed total dose. An exposure input improved these predictions around a temporary dose reduction whether or not the assumed clearance rate was correct, but reduced the predicted size of a dose effect, and a deterministic recurrent baseline matched ADMIT's average predictions. Exposure projection reduced constraint violations, although enforcement remained incomplete. Semi-synthetic experiments using eICU context illustrated treatment-response generation under fixed and adaptive policies. Observational examples further characterize model treatment sensitivity. ADMIT provides a framework for testing whether complementary observations and physiological restrictions improve intervention trajectories, with representation recovery, effect accuracy and rule enforcement assessed separately.
